Publications | Max Planck Institute for Intelligent Systems

2017

avg Mescheder, L., Nowozin, S., Geiger, A. The Numerics of GANs In Proceedings from the conference "Neural Information Processing Systems 2017., (Editors: Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.), Curran Associates, Inc., Advances in Neural Information Processing Systems 30 (NIPS), December 2017 (inproceedings)

data/model video code chumpy code tensorflow paper supplemental Project Page [BibTex]

Learning a model of facial shape and expression from 4D scans

Li, T., Bolkart, T., Black, M. J., Li, H., Romero, J.

ACM Transactions on Graphics, 36(6):194:1-194:17, November 2017, Two first authors contributed equally (article)

Abstract

The field of 3D face modeling has a large gap between high-end and low-end methods. At the high end, the best facial animation is indistinguishable from real humans, but this comes at the cost of extensive manual labor. At the low end, face capture from consumer depth sensors relies on 3D face models that are not expressive enough to capture the variability in natural facial shape and expression. We seek a middle ground by learning a facial model from thousands of accurately aligned 3D scans. Our FLAME model (Faces Learned with an Articulated Model and Expressions) is designed to work with existing graphics software and be easy to fit to data. FLAME uses a linear shape space trained from 3800 scans of human heads. FLAME combines this linear shape space with an articulated jaw, neck, and eyeballs, pose-dependent corrective blendshapes, and additional global expression from 4D face sequences in the D3DFACS dataset along with additional 4D sequences.We accurately register a template mesh to the scan sequences and make the D3DFACS registrations available for research purposes. In total the model is trained from over 33, 000 scans. FLAME is low-dimensional but more expressive than the FaceWarehouse model and the Basel Face Model. We compare FLAME to these models by fitting them to static 3D scans and 4D sequences using the same optimization method. FLAME is significantly more accurate and is available for research purposes (http://flame.is.tue.mpg.de).

ps Li, T., Bolkart, T., Black, M. J., Li, H., Romero, J. Learning a model of facial shape and expression from 4D scans ACM Transactions on Graphics, 36(6):194:1-194:17, November 2017, Two first authors contributed equally (article)

data/model video code chumpy code tensorflow paper supplemental Project Page [BibTex]

Investigating Body Image Disturbance in Anorexia Nervosa Using Novel Biometric Figure Rating Scales: A Pilot Study

Mölbert, S. C., Thaler, A., Streuber, S., Black, M. J., Karnath, H., Zipfel, S., Mohler, B., Giel, K. E.

European Eating Disorders Review, 25(6):607-612, November 2017 (article)

Abstract

This study uses novel biometric figure rating scales (FRS) spanning body mass index (BMI) 13.8 to 32.2 kg/m2 and BMI 18 to 42 kg/m2. The aims of the study were (i) to compare FRS body weight dissatisfaction and perceptual distortion of women with anorexia nervosa (AN) to a community sample; (ii) how FRS parameters are associated with questionnaire body dissatisfaction, eating disorder symptoms and appearance comparison habits; and (iii) whether the weight spectrum of the FRS matters. Women with AN (n = 24) and a community sample of women (n = 104) selected their current and ideal body on the FRS and completed additional questionnaires. Women with AN accurately picked the body that aligned best with their actual weight in both FRS. Controls underestimated their BMI in the FRS 14–32 and were accurate in the FRS 18–42. In both FRS, women with AN desired a body close to their actual BMI and controls desired a thinner body. Our observations suggest that body image disturbance in AN is unlikely to be characterized by a visual perceptual disturbance, but rather by an idealization of underweight in conjunction with high body dissatisfaction. The weight spectrum of FRS can influence the accuracy of BMI estimation.

publisher DOI Project Page [BibTex]

ps Mölbert, S. C., Thaler, A., Streuber, S., Black, M. J., Karnath, H., Zipfel, S., Mohler, B., Giel, K. E. Investigating Body Image Disturbance in Anorexia Nervosa Using Novel Biometric Figure Rating Scales: A Pilot Study European Eating Disorders Review, 25(6):607-612, November 2017 (article)

publisher DOI Project Page [BibTex]

Embodied Hands: Modeling and Capturing Hands and Bodies Together

Romero, J., Tzionas, D., Black, M. J.

ACM Transactions on Graphics, (Proc. SIGGRAPH Asia), 36(6):245:1-245:17, 245:1–245:17, ACM, November 2017 (article)

Abstract

Humans move their hands and bodies together to communicate and solve tasks. Capturing and replicating such coordinated activity is critical for virtual characters that behave realistically. Surprisingly, most methods treat the 3D modeling and tracking of bodies and hands separately. Here we formulate a model of hands and bodies interacting together and fit it to full-body 4D sequences. When scanning or capturing the full body in 3D, hands are small and often partially occluded, making their shape and pose hard to recover. To cope with low-resolution, occlusion, and noise, we develop a new model called MANO (hand Model with Articulated and Non-rigid defOrmations). MANO is learned from around 1000 high-resolution 3D scans of hands of 31 subjects in a wide variety of hand poses. The model is realistic, low-dimensional, captures non-rigid shape changes with pose, is compatible with standard graphics packages, and can fit any human hand. MANO provides a compact mapping from hand poses to pose blend shape corrections and a linear manifold of pose synergies. We attach MANO to a standard parameterized 3D body shape model (SMPL), resulting in a fully articulated body and hand model (SMPL+H). We illustrate SMPL+H by fitting complex, natural, activities of subjects captured with a 4D scanner. The fitting is fully automatic and results in full body models that move naturally with detailed hand motions and a realism not seen before in full body performance capture. The models and data are freely available for research purposes at http://mano.is.tue.mpg.de.

website youtube paper suppl video link (url) DOI Project Page [BibTex]

ps Romero, J., Tzionas, D., Black, M. J. Embodied Hands: Modeling and Capturing Hands and Bodies Together ACM Transactions on Graphics, (Proc. SIGGRAPH Asia), 36(6):245:1-245:17, 245:1–245:17, ACM, November 2017 (article)

website youtube paper suppl video link (url) DOI Project Page [BibTex]

A Generative Model of People in Clothing

Lassner, C., Pons-Moll, G., Gehler, P. V.

In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, IEEE International Conference on Computer Vision (ICCV), October 2017 (inproceedings)

Abstract

We present the first image-based generative model of people in clothing in a full-body setting. We sidestep the commonly used complex graphics rendering pipeline and the need for high-quality 3D scans of dressed people. Instead, we learn generative models from a large image database. The main challenge is to cope with the high variance in human pose, shape and appearance. For this reason, pure image-based approaches have not been considered so far. We show that this challenge can be overcome by splitting the generating process in two parts. First, we learn to generate a semantic segmentation of the body and clothing. Second, we learn a conditional model on the resulting segments that creates realistic images. The full model is differentiable and can be conditioned on pose, shape or color. The result are samples of people in different clothing items and styles. The proposed model can generate entirely new people with realistic clothing. In several experiments we present encouraging results that suggest an entirely data-driven approach to people generation is possible.

link (url) Project Page [BibTex]

ps Lassner, C., Pons-Moll, G., Gehler, P. V. A Generative Model of People in Clothing In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, IEEE International Conference on Computer Vision (ICCV), October 2017 (inproceedings)

link (url) Project Page [BibTex]

Semantic Video CNNs through Representation Warping

Gadde, R., Jampani, V., Gehler, P. V.

In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, IEEE International Conference on Computer Vision (ICCV), October 2017 (inproceedings) Accepted

Abstract

In this work, we propose a technique to convert CNN models for semantic segmentation of static images into CNNs for video data. We describe a warping method that can be used to augment existing architectures with very lit- tle extra computational cost. This module is called Net- Warp and we demonstrate its use for a range of network architectures. The main design principle is to use optical flow of adjacent frames for warping internal network repre- sentations across time. A key insight of this work is that fast optical flow methods can be combined with many different CNN architectures for improved performance and end-to- end training. Experiments validate that the proposed ap- proach incurs only little extra computational cost, while im- proving performance, when video streams are available. We achieve new state-of-the-art results on the standard CamVid and Cityscapes benchmark datasets and show reliable im- provements over different baseline networks. Our code and models are available at http://segmentation.is. tue.mpg.de

pdf Supplementary Project Page [BibTex]

ps Gadde, R., Jampani, V., Gehler, P. V. Semantic Video CNNs through Representation Warping In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, IEEE International Conference on Computer Vision (ICCV), October 2017 (inproceedings) Accepted

pdf Supplementary Project Page [BibTex]

Bounding Boxes, Segmentations and Object Coordinates: How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?

Behl, A., Jafari, O. H., Mustikovela, S. K., Alhaija, H. A., Rother, C., Geiger, A.

In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, IEEE International Conference on Computer Vision (ICCV), October 2017 (inproceedings)

Abstract

Existing methods for 3D scene flow estimation often fail in the presence of large displacement or local ambiguities, e.g., at texture-less or reflective surfaces. However, these challenges are omnipresent in dynamic road scenes, which is the focus of this work. Our main contribution is to overcome these 3D motion estimation problems by exploiting recognition. In particular, we investigate the importance of recognition granularity, from coarse 2D bounding box estimates over 2D instance segmentations to fine-grained 3D object part predictions. We compute these cues using CNNs trained on a newly annotated dataset of stereo images and integrate them into a CRF-based model for robust 3D scene flow estimation - an approach we term Instance Scene Flow. We analyze the importance of each recognition cue in an ablation study and observe that the instance segmentation cue is by far strongest, in our setting. We demonstrate the effectiveness of our method on the challenging KITTI 2015 scene flow benchmark where we achieve state-of-the-art performance at the time of submission.

avg

pdf suppmat Poster Project Page [BibTex]

avg Behl, A., Jafari, O. H., Mustikovela, S. K., Alhaija, H. A., Rother, C., Geiger, A. Bounding Boxes, Segmentations and Object Coordinates: How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios? In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, IEEE International Conference on Computer Vision (ICCV), October 2017 (inproceedings)

pdf suppmat Poster Project Page [BibTex]

A simple yet effective baseline for 3d human pose estimation

Martinez, J., Hossain, R., Romero, J., Little, J. J.

In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, IEEE International Conference on Computer Vision (ICCV), October 2017 (inproceedings)

Abstract

Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels. Despite their excellent performance, it is often not easy to understand whether their remaining error stems from a limited 2d pose (visual) understanding, or from a failure to map 2d poses into 3-dimensional positions. With the goal of understanding these sources of error, we set out to build a system that given 2d joint locations predicts 3d positions. Much to our surprise, we have found that, with current technology, "lifting" ground truth 2d joint locations to 3d space is a task that can be solved with a remarkably low error rate: a relatively simple deep feed-forward network outperforms the best reported result by about 30\% on Human3.6M, the largest publicly available 3d pose estimation benchmark. Furthermore, training our system on the output of an off-the-shelf state-of-the-art 2d detector (\ie, using images as input) yields state of the art results -- this includes an array of systems that have been trained end-to-end specifically for this task. Our results indicate that a large portion of the error of modern deep 3d pose estimation systems stems from their visual analysis, and suggests directions to further advance the state of the art in 3d human pose estimation.

video code arxiv pdf preprint Project Page [BibTex]

ps Martinez, J., Hossain, R., Romero, J., Little, J. J. A simple yet effective baseline for 3d human pose estimation In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, IEEE International Conference on Computer Vision (ICCV), October 2017 (inproceedings)

video code arxiv pdf preprint Project Page [BibTex]

Sparsity Invariant CNNs

Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A.

International Conference on 3D Vision (3DV) 2017, International Conference on 3D Vision (3DV), October 2017 (conference)

Abstract

In this paper, we consider convolutional neural networks operating on sparse inputs with an application to depth upsampling from sparse laser scan data. First, we show that traditional convolutional networks perform poorly when applied to sparse data even when the location of missing data is provided to the network. To overcome this problem, we propose a simple yet effective sparse convolution layer which explicitly considers the location of missing data during the convolution operation. We demonstrate the benefits of the proposed network architecture in synthetic and real experiments \wrt various baseline approaches. Compared to dense baselines, the proposed sparse convolution network generalizes well to novel datasets and is invariant to the level of sparsity in the data. For our evaluation, we derive a novel dataset from the KITTI benchmark, comprising 93k depth annotated RGB images. Our dataset allows for training and evaluating depth upsampling and depth prediction techniques in challenging real-world settings.

avg

avg Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A. Sparsity Invariant CNNs International Conference on 3D Vision (3DV) 2017, International Conference on 3D Vision (3DV), October 2017 (conference)

pdf Video 1 Video 2 Project Page Project Page [BibTex]

OctNetFusion: Learning Depth Fusion from Data

Riegler, G., Ulusoy, A. O., Bischof, H., Geiger, A.

International Conference on 3D Vision (3DV) 2017, International Conference on 3D Vision (3DV), October 2017 (conference)

Abstract

In this paper, we present a learning based approach to depth fusion, i.e., dense 3D reconstruction from multiple depth images. The most common approach to depth fusion is based on averaging truncated signed distance functions, which was originally proposed by Curless and Levoy in 1996. While this method is simple and provides great results, it is not able to reconstruct (partially) occluded surfaces and requires a large number frames to filter out sensor noise and outliers. Motivated by the availability of large 3D model repositories and recent advances in deep learning, we present a novel 3D CNN architecture that learns to predict an implicit surface representation from the input depth maps. Our learning based method significantly outperforms the traditional volumetric fusion approach in terms of noise reduction and outlier suppression. By learning the structure of real world 3D objects and scenes, our approach is further able to reconstruct occluded regions and to fill in gaps in the reconstruction. We demonstrate that our learning based approach outperforms both vanilla TSDF fusion as well as TV-L1 fusion on the task of volumetric fusion. Further, we demonstrate state-of-the-art 3D shape completion results.

avg

avg Riegler, G., Ulusoy, A. O., Bischof, H., Geiger, A. OctNetFusion: Learning Depth Fusion from Data International Conference on 3D Vision (3DV) 2017, International Conference on 3D Vision (3DV), October 2017 (conference)

pdf Video 1 Video 2 Project Page Project Page [BibTex]

An Online Scalable Approach to Unified Multirobot Cooperative Localization and Object Tracking

Ahmad, A., Lawless, G., Lima, P.

IEEE Transactions on Robotics (T-RO), 33, pages: 1184 - 1199, October 2017 (article)

Abstract

In this article we present a unified approach for multi-robot cooperative simultaneous localization and object tracking based on particle filters. Our approach is scalable with respect to the number of robots in the team. We introduce a method that reduces, from an exponential to a linear growth, the space and computation time requirements with respect to the number of robots in order to maintain a given level of accuracy in the full state estimation. Our method requires no increase in the number of particles with respect to the number of robots. However, in our method each particle represents a full state hypothesis, leading to the linear dependency on the number of robots of both space and time complexity. The derivation of the algorithm implementing our approach from a standard particle filter algorithm and its complexity analysis are presented. Through an extensive set of simulation experiments on a large number of randomized datasets, we demonstrate the correctness and efficacy of our approach. Through real robot experiments on a standardized open dataset of a team of four soccer playing robots tracking a ball, we evaluate our method's estimation accuracy with respect to the ground truth values. Through comparisons with other methods based on i) nonlinear least squares minimization and ii) joint extended Kalman filter, we further highlight our method's advantages. Finally, we also present a robustness test for our approach by evaluating it under scenarios of communication and vision failure in teammate robots.

Published Version link (url) DOI [BibTex]

ps Ahmad, A., Lawless, G., Lima, P. An Online Scalable Approach to Unified Multirobot Cooperative Localization and Object Tracking IEEE Transactions on Robotics (T-RO), 33, pages: 1184 - 1199, October 2017 (article)

Published Version link (url) DOI [BibTex]

Direct Visual Odometry for a Fisheye-Stereo Camera

Liu, P., Heng, L., Sattler, T., Geiger, A., Pollefeys, M.

In Proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Piscataway, NJ, USA, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 2017 (inproceedings)

Abstract

We present a direct visual odometry algorithm for a fisheye-stereo camera. Our algorithm performs simultaneous camera motion estimation and semi-dense reconstruction. The pipeline consists of two threads: a tracking thread and a mapping thread. In the tracking thread, we estimate the camera pose via semi-dense direct image alignment. To have a wider field of view (FoV) which is important for robotic perception, we use fisheye images directly without converting them to conventional pinhole images which come with a limited FoV. To address the epipolar curve problem, plane-sweeping stereo is used for stereo matching and depth initialization. Multiple depth hypotheses are tracked for selected pixels to better capture the uncertainty characteristics of stereo matching. Temporal motion stereo is then used to refine the depth and remove false positive depth hypotheses. Our implementation runs at an average of 20 Hz on a low-end PC. We run experiments in outdoor environments to validate our algorithm, and discuss the experimental results. We experimentally show that we are able to estimate 6D poses with low drift, and at the same time, do semi-dense 3D reconstruction with high accuracy.

avg

avg Liu, P., Heng, L., Sattler, T., Geiger, A., Pollefeys, M. Direct Visual Odometry for a Fisheye-Stereo Camera In Proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Piscataway, NJ, USA, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 2017 (inproceedings)

Augmented Reality Meets Deep Learning for Car Instance Segmentation in Urban Scenes

Alhaija, H. A., Mustikovela, S. K., Mescheder, L., Geiger, A., Rother, C.

In Proceedings of the British Machine Vision Conference 2017, Proceedings of the British Machine Vision Conference, September 2017 (inproceedings)

Abstract

The success of deep learning in computer vision is based on the availability of large annotated datasets. To lower the need for hand labeled images, virtually rendered 3D worlds have recently gained popularity. Unfortunately, creating realistic 3D content is challenging on its own and requires significant human effort. In this work, we propose an alternative paradigm which combines real and synthetic data for learning semantic instance segmentation models. Exploiting the fact that not all aspects of the scene are equally important for this task, we propose to augment real-world imagery with virtual objects of the target category. Capturing real-world images at large scale is easy and cheap, and directly provides real background appearances without the need for creating complex 3D models of the environment. We present an efficient procedure to augment these images with virtual objects. This allows us to create realistic composite images which exhibit both realistic background appearance as well as a large number of complex object arrangements. In contrast to modeling complete 3D environments, our data augmentation approach requires only a few user interactions in combination with 3D shapes of the target object category. We demonstrate the utility of the proposed approach for training a state-of-the-art high-capacity deep model for semantic instance segmentation. In particular, we consider the task of segmenting car instances on the KITTI dataset which we have annotated with pixel-accurate ground truth. Our experiments demonstrate that models trained on augmented imagery generalize better than those trained on synthetic data or models trained on limited amounts of annotated real data.

avg

avg Alhaija, H. A., Mustikovela, S. K., Mescheder, L., Geiger, A., Rother, C. Augmented Reality Meets Deep Learning for Car Instance Segmentation in Urban Scenes In Proceedings of the British Machine Vision Conference 2017, Proceedings of the British Machine Vision Conference, September 2017 (inproceedings)

pdf suppmat Project Page arxiv-version Project Page [BibTex]

Effects of animation retargeting on perceived action outcomes

Kenny, S., Mahmood, N., Honda, C., Black, M. J., Troje, N. F.

Proceedings of the ACM Symposium on Applied Perception (SAP’17), pages: 2:1-2:7, September 2017 (conference)

Abstract

The individual shape of the human body, including the geometry of its articulated structure and the distribution of weight over that structure, influences the kinematics of a person's movements. How sensitive is the visual system to inconsistencies between shape and motion introduced by retargeting motion from one person onto the shape of another? We used optical motion capture to record five pairs of male performers with large differences in body weight, while they pushed, lifted, and threw objects. Based on a set of 67 markers, we estimated both the kinematics of the actions as well as the performer's individual body shape. To obtain consistent and inconsistent stimuli, we created animated avatars by combining the shape and motion estimates from either a single performer or from different performers. In a virtual reality environment, observers rated the perceived weight or thrown distance of the objects. They were also asked to explicitly discriminate between consistent and hybrid stimuli. Observers were unable to accomplish the latter, but hybridization of shape and motion influenced their judgements of action outcome in systematic ways. Inconsistencies between shape and motion were assimilated into an altered perception of the action outcome.

pdf DOI [BibTex]

ps Kenny, S., Mahmood, N., Honda, C., Black, M. J., Troje, N. F. Effects of animation retargeting on perceived action outcomes Proceedings of the ACM Symposium on Applied Perception (SAP’17), pages: 2:1-2:7, September 2017 (conference)

pdf DOI [BibTex]

Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks

Mescheder, L., Nowozin, S., Geiger, A.

In Proceedings of the 34th International Conference on Machine Learning, 70, Proceedings of Machine Learning Research, (Editors: Doina Precup, Yee Whye Teh), PMLR, International Conference on Machine Learning (ICML), August 2017 (inproceedings)

Abstract

Variational Autoencoders (VAEs) are expressive latent variable models that can be used to learn complex probability distributions from training data. However, the quality of the resulting model crucially relies on the expressiveness of the inference model. We introduce Adversarial Variational Bayes (AVB), a technique for training Variational Autoencoders with arbitrarily expressive inference models. We achieve this by introducing an auxiliary discriminative network that allows to rephrase the maximum-likelihood-problem as a two-player game, hence establishing a principled connection between VAEs and Generative Adversarial Networks (GANs). We show that in the nonparametric limit our method yields an exact maximum-likelihood assignment for the parameters of the generative model, as well as the exact posterior distribution over the latent variables given an observation. Contrary to competing approaches which combine VAEs with GANs, our approach has a clear theoretical justification, retains most advantages of standard Variational Autoencoders and is easy to implement.

avg

avg Mescheder, L., Nowozin, S., Geiger, A. Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks In Proceedings of the 34th International Conference on Machine Learning, 70, Proceedings of Machine Learning Research, (Editors: Doina Precup, Yee Whye Teh), PMLR, International Conference on Machine Learning (ICML), August 2017 (inproceedings)

pdf suppmat Project Page arxiv-version Project Page [BibTex]

Coupling Adaptive Batch Sizes with Learning Rates

Balles, L., Romero, J., Hennig, P.

In Proceedings Conference on Uncertainty in Artificial Intelligence (UAI) 2017, pages: 410-419, (Editors: Gal Elidan and Kristian Kersting), Association for Uncertainty in Artificial Intelligence (AUAI), Conference on Uncertainty in Artificial Intelligence (UAI), August 2017 (inproceedings)

Abstract

Mini-batch stochastic gradient descent and variants thereof have become standard for large-scale empirical risk minimization like the training of neural networks. These methods are usually used with a constant batch size chosen by simple empirical inspection. The batch size significantly influences the behavior of the stochastic optimization algorithm, though, since it determines the variance of the gradient estimates. This variance also changes over the optimization process; when using a constant batch size, stability and convergence is thus often enforced by means of a (manually tuned) decreasing learning rate schedule. We propose a practical method for dynamic batch size adaptation. It estimates the variance of the stochastic gradients and adapts the batch size to decrease the variance proportionally to the value of the objective function, removing the need for the aforementioned learning rate decrease. In contrast to recent related work, our algorithm couples the batch size to the learning rate, directly reflecting the known relationship between the two. On three image classification benchmarks, our batch size adaptation yields faster optimization convergence, while simultaneously simplifying learning rate tuning. A TensorFlow implementation is available.

ps pn

Code link (url) Project Page [BibTex]

ps pn Balles, L., Romero, J., Hennig, P. Coupling Adaptive Batch Sizes with Learning Rates In Proceedings Conference on Uncertainty in Artificial Intelligence (UAI) 2017, pages: 410-419, (Editors: Gal Elidan and Kristian Kersting), Association for Uncertainty in Artificial Intelligence (AUAI), Conference on Uncertainty in Artificial Intelligence (UAI), August 2017 (inproceedings)

Code link (url) Project Page [BibTex]

Learning local feature aggregation functions with backpropagation

Paschalidou, D., Katharopoulos, A., Diou, C., Delopoulos, A.

In IEEE, Signal Processing Conference (EUSIPCO), 25th European, August 2017 (inproceedings)

Abstract

This paper introduces a family of local feature aggregation functions and a novel method to estimate their parameters, such that they generate optimal representations for classification (or any task that can be expressed as a cost function minimization problem). To achieve that, we compose the local feature aggregation function with the classifier cost function and we backpropagate the gradient of this cost function in order to update the local feature aggregation function parameters. Experiments on synthetic datasets indicate that our method discovers parameters that model the class-relevant information in addition to the local feature space. Further experiments on a variety of motion and visual descriptors, both on image and video datasets, show that our method outperforms other state-of-the-art local feature aggregation functions, such as Bag of Words, Fisher Vectors and VLAD, by a large margin.

avg

pdf code poster link (url) DOI [BibTex]

avg Paschalidou, D., Katharopoulos, A., Diou, C., Delopoulos, A. Learning local feature aggregation functions with backpropagation In IEEE, Signal Processing Conference (EUSIPCO), 25th European, August 2017 (inproceedings)

pdf code poster link (url) DOI [BibTex]

Joint Graph Decomposition and Node Labeling by Local Search

Levinkov, E., Uhrig, J., Tang, S., Omran, M., Insafutdinov, E., Kirillov, A., Rother, C., Brox, T., Schiele, B., Andres, B.

In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 1904-1912, IEEE, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

PDF Supplementary DOI Project Page [BibTex]

ps Levinkov, E., Uhrig, J., Tang, S., Omran, M., Insafutdinov, E., Kirillov, A., Rother, C., Brox, T., Schiele, B., Andres, B. Joint Graph Decomposition and Node Labeling by Local Search In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 1904-1912, IEEE, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

PDF Supplementary DOI Project Page [BibTex]

Dynamic FAUST: Registering Human Bodies in Motion

Bogo, F., Romero, J., Pons-Moll, G., Black, M. J.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

Abstract

While the ready availability of 3D scan data has influenced research throughout computer vision, less attention has focused on 4D data; that is 3D scans of moving nonrigid objects, captured over time. To be useful for vision research, such 4D scans need to be registered, or aligned, to a common topology. Consequently, extending mesh registration methods to 4D is important. Unfortunately, no ground-truth datasets are available for quantitative evaluation and comparison of 4D registration methods. To address this we create a novel dataset of high-resolution 4D scans of human subjects in motion, captured at 60 fps. We propose a new mesh registration method that uses both 3D geometry and texture information to register all scans in a sequence to a common reference topology. The approach exploits consistency in texture over both short and long time intervals and deals with temporal offsets between shape and texture capture. We show how using geometry alone results in significant errors in alignment when the motions are fast and non-rigid. We evaluate the accuracy of our registration and provide a dataset of 40,000 raw and aligned meshes. Dynamic FAUST extends the popular FAUST dataset to dynamic 4D data, and is available for research purposes at http://dfaust.is.tue.mpg.de.

pdf video Project Page Project Page Project Page [BibTex]

ps Bogo, F., Romero, J., Pons-Moll, G., Black, M. J. Dynamic FAUST: Registering Human Bodies in Motion In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

pdf video Project Page Project Page Project Page [BibTex]

Learning from Synthetic Humans

Varol, G., Romero, J., Martin, X., Mahmood, N., Black, M. J., Laptev, I., Schmid, C.

Abstract

Estimating human pose, shape, and motion from images and videos are fundamental challenges with many applications. Recent advances in 2D human pose estimation use large amounts of manually-labeled training data for learning convolutional neural networks (CNNs). Such data is time consuming to acquire and difficult to extend. Moreover, manual labeling of 3D pose, depth and motion is impractical. In this work we present SURREAL (Synthetic hUmans foR REAL tasks): a new large-scale dataset with synthetically-generated but realistic images of people rendered from 3D sequences of human motion capture data. We generate more than 6 million frames together with ground truth pose, depth maps, and segmentation masks. We show that CNNs trained on our synthetic dataset allow for accurate human depth estimation and human part segmentation in real RGB images. Our results and the new dataset open up new possibilities for advancing person analysis using cheap and large-scale synthetic data.

arXiv project data Project Page Project Page [BibTex]

ps Varol, G., Romero, J., Martin, X., Mahmood, N., Black, M. J., Laptev, I., Schmid, C. Learning from Synthetic Humans In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

arXiv project data Project Page Project Page [BibTex]

On human motion prediction using recurrent neural networks

Martinez, J., Black, M. J., Romero, J.

Abstract

Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented reality. Following the success of deep learning methods in several computer vision tasks, recent work has focused on using deep recurrent neural networks (RNNs) to model human motion, with the goal of learning time-dependent representations that perform tasks such as short-term motion prediction and long-term human motion synthesis. We examine recent work, with a focus on the evaluation methodologies commonly used in the literature, and show that, surprisingly, state-of-the-art performance can be achieved by a simple baseline that does not attempt to model motion at all. We investigate this result, and analyze recent RNN methods by looking at the architectures, loss functions, and training procedures used in state-of-the-art approaches. We propose three changes to the standard RNN models typically used for human motion, which result in a simple and scalable RNN architecture that obtains state-of-the-art performance on human motion prediction.

ps Martinez, J., Black, M. J., Romero, J. On human motion prediction using recurrent neural networks In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

Wulff, J., Sevilla-Lara, L., Black, M. J.

Articulated Multi-person Tracking in the Wild

Insafutdinov, E., Andriluka, M., Pishchulin, L., Tang, S., Levinkov, E., Andres, B., Schiele, B.

In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 1293-1301, IEEE, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017, Oral (inproceedings)

DOI [BibTex]

ps Insafutdinov, E., Andriluka, M., Pishchulin, L., Tang, S., Levinkov, E., Andres, B., Schiele, B. Articulated Multi-person Tracking in the Wild In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 1293-1301, IEEE, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017, Oral (inproceedings)

DOI [BibTex]

Slow Flow: Exploiting High-Speed Cameras for Accurate and Diverse Optical Flow Reference Data

Janai, J., Güney, F., Wulff, J., Black, M., Geiger, A.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, pages: 1406-1416, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

Abstract

Existing optical flow datasets are limited in size and variability due to the difficulty of capturing dense ground truth. In this paper, we tackle this problem by tracking pixels through densely sampled space-time volumes recorded with a high-speed video camera. Our model exploits the linearity of small motions and reasons about occlusions from multiple frames. Using our technique, we are able to establish accurate reference flow fields outside the laboratory in natural environments. Besides, we show how our predictions can be used to augment the input images with realistic motion blur. We demonstrate the quality of the produced flow fields on synthetic and real-world datasets. Finally, we collect a novel challenging optical flow dataset by applying our technique on data from a high-speed camera and analyze the performance of the state-of-the-art in optical flow under various levels of motion blur.

avg ps

pdf suppmat Project page Video DOI Project Page [BibTex]

avg ps Janai, J., Güney, F., Wulff, J., Black, M., Geiger, A. Slow Flow: Exploiting High-Speed Cameras for Accurate and Diverse Optical Flow Reference Data In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, pages: 1406-1416, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

pdf suppmat Project page Video DOI Project Page [BibTex]

Optical Flow in Mostly Rigid Scenes

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, pages: 6911-6920, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

Abstract

The optical flow of natural scenes is a combination of the motion of the observer and the independent motion of objects. Existing algorithms typically focus on either recovering motion and structure under the assumption of a purely static world or optical flow for general unconstrained scenes. We combine these approaches in an optical flow algorithm that estimates an explicit segmentation of moving objects from appearance and physical constraints. In static regions we take advantage of strong constraints to jointly estimate the camera motion and the 3D structure of the scene over multiple frames. This allows us to also regularize the structure instead of the motion. Our formulation uses a Plane+Parallax framework, which works even under small baselines, and reduces the motion estimation to a one-dimensional search problem, resulting in more accurate estimation. In moving regions the flow is treated as unconstrained, and computed with an existing optical flow method. The resulting Mostly-Rigid Flow (MR-Flow) method achieves state-of-the-art results on both the MPISintel and KITTI-2015 benchmarks.

pdf SupMat video code Project Page [BibTex]

ps Wulff, J., Sevilla-Lara, L., Black, M. J. Optical Flow in Mostly Rigid Scenes In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, pages: 6911-6920, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

pdf SupMat video code Project Page [BibTex]

OctNet: Learning Deep 3D Representations at High Resolutions

Riegler, G., Ulusoy, O., Geiger, A.

Abstract

We present OctNet, a representation for deep learning with sparse 3D data. In contrast to existing models, our representation enables 3D convolutional networks which are both deep and high resolution. Towards this goal, we exploit the sparsity in the input data to hierarchically partition the space using a set of unbalanced octrees where each leaf node stores a pooled feature representation. This allows to focus memory allocation and computation to the relevant dense regions and enables deeper networks without compromising resolution. We demonstrate the utility of our OctNet representation by analyzing the impact of resolution on several 3D tasks including 3D object classification, orientation estimation and point cloud labeling.

avg ps

pdf suppmat Project Page Video Project Page [BibTex]

avg ps Riegler, G., Ulusoy, O., Geiger, A. OctNet: Learning Deep 3D Representations at High Resolutions In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

pdf suppmat Project Page Video Project Page [BibTex]

Reflectance Adaptive Filtering Improves Intrinsic Image Estimation

Nestmeyer, T., Gehler, P. V.

In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 1771-1780, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

pre-print DOI Project Page Project Page [BibTex]

ps Nestmeyer, T., Gehler, P. V. Reflectance Adaptive Filtering Improves Intrinsic Image Estimation In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 1771-1780, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

pre-print DOI Project Page Project Page [BibTex]

A Multi-View Stereo Benchmark with High-Resolution Images and Multi-Camera Videos

Schöps, T., Schönberger, J. L., Galliani, S., Sattler, T., Schindler, K., Pollefeys, M., Geiger, A.

Abstract

Motivated by the limitations of existing multi-view stereo benchmarks, we present a novel dataset for this task. Towards this goal, we recorded a variety of indoor and outdoor scenes using a high-precision laser scanner and captured both high-resolution DSLR imagery as well as synchronized low-resolution stereo videos with varying fields-of-view. To align the images with the laser scans, we propose a robust technique which minimizes photometric errors conditioned on the geometry. In contrast to previous datasets, our benchmark provides novel challenges and covers a diverse set of viewpoints and scene types, ranging from natural scenes to man-made indoor and outdoor environments. Furthermore, we provide data at significantly higher temporal and spatial resolution. Our benchmark is the first to cover the important use case of hand-held mobile devices while also providing high-resolution DSLR camera images. We make our datasets and an online evaluation server available at http://www.eth3d.net.

avg

avg Schöps, T., Schönberger, J. L., Galliani, S., Sattler, T., Schindler, K., Pollefeys, M., Geiger, A. A Multi-View Stereo Benchmark with High-Resolution Images and Multi-Camera Videos In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

arxiv_preprint video dataset pdf supplemental DOI Project Page [BibTex]

Detailed, accurate, human shape estimation from clothed 3D scan sequences

Zhang, C., Pujades, S., Black, M., Pons-Moll, G.

In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, Washington, DC, USA, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), July 2017, Spotlight (inproceedings)

Abstract

We address the problem of estimating human body shape from 3D scans over time. Reliable estimation of 3D body shape is necessary for many applications including virtual try-on, health monitoring, and avatar creation for virtual reality. Scanning bodies in minimal clothing, however, presents a practical barrier to these applications. We address this problem by estimating body shape under clothing from a sequence of 3D scans. Previous methods that have exploited statistical models of body shape produce overly smooth shapes lacking personalized details. In this paper we contribute a new approach to recover not only an approximate shape of the person, but also their detailed shape. Our approach allows the estimated shape to deviate from a parametric model to fit the 3D scans. We demonstrate the method using high quality 4D data as well as sequences of visual hulls extracted from multi-view images. We also make available a new high quality 4D dataset that enables quantitative evaluation. Our method outperforms the previous state of the art, both qualitatively and quantitatively.

ps Zhang, C., Pujades, S., Black, M., Pons-Moll, G. Detailed, accurate, human shape estimation from clothed 3D scan sequences In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, Washington, DC, USA, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), July 2017, Spotlight (inproceedings)

arxiv_preprint video dataset pdf supplemental DOI Project Page [BibTex]

3D Menagerie: Modeling the 3D Shape and Pose of Animals

Zuffi, S., Kanazawa, A., Jacobs, D., Black, M. J.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, pages: 5524-5532, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

Abstract

There has been significant work on learning realistic, articulated, 3D models of the human body. In contrast, there are few such models of animals, despite many applications. The main challenge is that animals are much less cooperative than humans. The best human body models are learned from thousands of 3D scans of people in specific poses, which is infeasible with live animals. Consequently, we learn our model from a small set of 3D scans of toy figurines in arbitrary poses. We employ a novel part-based shape model to compute an initial registration to the scans. We then normalize their pose, learn a statistical shape model, and refine the registrations and the model together. In this way, we accurately align animal scans from different quadruped families with very different shapes and poses. With the registration to a common template we learn a shape space representing animals including lions, cats, dogs, horses, cows and hippos. Animal shapes can be sampled from the model, posed, animated, and fit to data. We demonstrate generalization by fitting it to images of real animals including species not seen in training.

pdf video Project Page [BibTex]

ps Zuffi, S., Kanazawa, A., Jacobs, D., Black, M. J. 3D Menagerie: Modeling the 3D Shape and Pose of Animals In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, pages: 5524-5532, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

pdf video Project Page [BibTex]

Toroidal Constraints for Two Point Localization Under High Outlier Ratios

Camposeco, F., Sattler, T., Cohen, A., Geiger, A., Pollefeys, M.

Abstract

Localizing a query image against a 3D model at large scale is a hard problem, since 2D-3D matches become more and more ambiguous as the model size increases. This creates a need for pose estimation strategies that can handle very low inlier ratios. In this paper, we draw new insights on the geometric information available from the 2D-3D matching process. As modern descriptors are not invariant against large variations in viewpoint, we are able to find the rays in space used to triangulate a given point that are closest to a query descriptor. It is well known that two correspondences constrain the camera to lie on the surface of a torus. Adding the knowledge of direction of triangulation, we are able to approximate the position of the camera from \emphtwo matches alone. We derive a geometric solver that can compute this position in under 1 microsecond. Using this solver, we propose a simple yet powerful outlier filter which scales quadratically in the number of matches. We validate the accuracy of our solver and demonstrate the usefulness of our method in real world settings.

avg

pdf suppmat Project Page pdf Project Page [BibTex]

avg Camposeco, F., Sattler, T., Cohen, A., Geiger, A., Pollefeys, M. Toroidal Constraints for Two Point Localization Under High Outlier Ratios In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

Optical Flow Estimation using a Spatial Pyramid Network

Ranjan, A., Black, M.

Abstract

We learn to compute optical flow by combining a classical spatial-pyramid formulation with deep learning. This estimates large motions in a coarse-to-fine approach by warping one image of a pair at each pyramid level by the current flow estimate and computing an update to the flow. Instead of the standard minimization of an objective function at each pyramid level, we train one deep network per level to compute the flow update. Unlike the recent FlowNet approach, the networks do not need to deal with large motions; these are dealt with by the pyramid. This has several advantages. First, our Spatial Pyramid Network (SPyNet) is much simpler and 96% smaller than FlowNet in terms of model parameters. This makes it more efficient and appropriate for embedded applications. Second, since the flow at each pyramid level is small (< 1 pixel), a convolutional approach applied to pairs of warped images is appropriate. Third, unlike FlowNet, the learned convolution filters appear similar to classical spatio-temporal filters, giving insight into the method and how to improve it. Our results are more accurate than FlowNet on most standard benchmarks, suggesting a new direction of combining classical flow methods with deep learning.

pdf SupMat project/code [BibTex]

ps Ranjan, A., Black, M. Optical Flow Estimation using a Spatial Pyramid Network In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

pdf SupMat project/code [BibTex]

Multiple People Tracking by Lifted Multicut and Person Re-identification

Tang, S., Andriluka, M., Andres, B., Schiele, B.

In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 3701-3710, IEEE Computer Society, Washington, DC, USA, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

DOI Project Page [BibTex]

ps Tang, S., Andriluka, M., Andres, B., Schiele, B. Multiple People Tracking by Lifted Multicut and Person Re-identification In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 3701-3710, IEEE Computer Society, Washington, DC, USA, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

DOI Project Page [BibTex]

Video Propagation Networks

Jampani, V., Gadde, R., Gehler, P. V.

pdf supplementary arXiv project page code Project Page [BibTex]

ps Jampani, V., Gadde, R., Gehler, P. V. Video Propagation Networks In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

pdf supplementary arXiv project page code Project Page [BibTex]

Generating Descriptions with Grounded and Co-Referenced People

Rohrbach, A., Rohrbach, M., Tang, S., Oh, S. J., Schiele, B.

In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 4196-4206, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

PDF DOI Project Page [BibTex]

ps Rohrbach, A., Rohrbach, M., Tang, S., Oh, S. J., Schiele, B. Generating Descriptions with Grounded and Co-Referenced People In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 4196-4206, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

PDF DOI Project Page [BibTex]

Semantic Multi-view Stereo: Jointly Estimating Objects and Voxels

Ulusoy, A. O., Black, M. J., Geiger, A.

Abstract

Dense 3D reconstruction from RGB images is a highly ill-posed problem due to occlusions, textureless or reflective surfaces, as well as other challenges. We propose object-level shape priors to address these ambiguities. Towards this goal, we formulate a probabilistic model that integrates multi-view image evidence with 3D shape information from multiple objects. Inference in this model yields a dense 3D reconstruction of the scene as well as the existence and precise 3D pose of the objects in it. Our approach is able to recover fine details not captured in the input shapes while defaulting to the input models in occluded regions where image evidence is weak. Due to its probabilistic nature, the approach is able to cope with the approximate geometry of the 3D models as well as input shapes that are not present in the scene. We evaluate the approach quantitatively on several challenging indoor and outdoor datasets.

avg ps

YouTube pdf suppmat Project Page [BibTex]

avg ps Ulusoy, A. O., Black, M. J., Geiger, A. Semantic Multi-view Stereo: Jointly Estimating Objects and Voxels In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

YouTube pdf suppmat Project Page [BibTex]

Deep representation learning for human motion prediction and classification

Bütepage, J., Black, M., Kragic, D., Kjellström, H.

Abstract

Generative models of 3D human motion are often restricted to a small number of activities and can therefore not generalize well to novel movements or applications. In this work we propose a deep learning framework for human motion capture data that learns a generic representation from a large corpus of motion capture data and generalizes well to new, unseen, motions. Using an encoding-decoding network that learns to predict future 3D poses from the most recent past, we extract a feature representation of human motion. Most work on deep learning for sequence prediction focuses on video and speech. Since skeletal data has a different structure, we present and evaluate different network architectures that make different assumptions about time dependencies and limb correlations. To quantify the learned features, we use the output of different layers for action classification and visualize the receptive fields of the network units. Our method outperforms the recent state of the art in skeletal motion prediction even though these use action specific training data. Our results show that deep feedforward networks, trained from a generic mocap database, can successfully be used for feature extraction from human motion data and that this representation can be used as a foundation for classification and prediction.

ps Bütepage, J., Black, M., Kragic, D., Kjellström, H. Deep representation learning for human motion prediction and classification In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

arXiv project/code/data Project Page [BibTex]

Unite the People: Closing the Loop Between 3D and 2D Human Representations

Lassner, C., Romero, J., Kiefel, M., Bogo, F., Black, M. J., Gehler, P. V.

Abstract

3D models provide a common ground for different representations of human bodies. In turn, robust 2D estimation has proven to be a powerful tool to obtain 3D fits “in-the-wild”. However, depending on the level of detail, it can be hard to impossible to acquire labeled data for training 2D estimators on large scale. We propose a hybrid approach to this problem: with an extended version of the recently introduced SMPLify method, we obtain high quality 3D body model fits for multiple human pose datasets. Human annotators solely sort good and bad fits. This procedure leads to an initial dataset, UP-3D, with rich annotations. With a comprehensive set of experiments, we show how this data can be used to train discriminative models that produce results with an unprecedented level of detail: our models predict 31 segments and 91 landmark locations on the body. Using the 91 landmark pose estimator, we present state-of-the art results for 3D human pose and shape estimation using an order of magnitude less training data and without assumptions about gender or pose in the fitting procedure. We show that UP-3D can be enhanced with these improved fits to grow in quantity and quality, which makes the system deployable on large scale. The data, code and models are available for research purposes.

ps Lassner, C., Romero, J., Kiefel, M., Bogo, F., Black, M. J., Gehler, P. V. Unite the People: Closing the Loop Between 3D and 2D Human Representations In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

arXiv project/code/data Project Page [BibTex]

Early Stopping Without a Validation Set

Mahsereci, M., Balles, L., Lassner, C., Hennig, P.

arXiv preprint arXiv:1703.09580, 2017 (article)

Abstract

Early stopping is a widely used technique to prevent poor generalization performance when training an over-expressive model by means of gradient-based optimization. To find a good point to halt the optimizer, a common practice is to split the dataset into a training and a smaller validation set to obtain an ongoing estimate of the generalization performance. In this paper we propose a novel early stopping criterion which is based on fast-to-compute, local statistics of the computed gradients and entirely removes the need for a held-out validation set. Our experiments show that this is a viable approach in the setting of least-squares and logistic regression as well as neural networks.

ps pn

link (url) Project Page Project Page [BibTex]

ps pn Mahsereci, M., Balles, L., Lassner, C., Hennig, P. Early Stopping Without a Validation Set arXiv preprint arXiv:1703.09580, 2017 (article)

link (url) Project Page Project Page [BibTex]

SurfaceNet: An End-to-End 3D Neural Network for Multiview Stereopsis

Ji, M., Gall, J., Zheng, H., Liu, Y., Fang, L.

In IEEE International Conference on Computer Vision (ICCV), 2017, IEEE Computer Society, 2017 IEEE International Conference on Computer Vision (ICCV), 2017 (inproceedings)

Abstract

This paper proposes an end-to-end learning framework for multiview stereopsis. We term the network SurfaceNet. It takes a set of images and their corresponding camera parameters as input and directly infers the 3D model. The key advantage of the framework is that both photo-consistency as well geometric relations of the surface structure can be directly learned for the purpose of multiview stereopsis in an end-to-end fashion. SurfaceNet is a fully 3D convolutional network which is achieved by encoding the camera parameters together with the images in a 3D voxel representation. We evaluate SurfaceNet on the large-scale DTU benchmark. Code is available in https://github.com/mjiUST/SurfaceNet

avg

link (url) [BibTex]

avg Ji, M., Gall, J., Zheng, H., Liu, Y., Fang, L. SurfaceNet: An End-to-End 3D Neural Network for Multiview Stereopsis In IEEE International Conference on Computer Vision (ICCV), 2017, IEEE Computer Society, 2017 IEEE International Conference on Computer Vision (ICCV), 2017 (inproceedings)

link (url) [BibTex]

Self-Organized Behavior Generation for Musculoskeletal Robots

Der, R., Martius, G.

Frontiers in Neurorobotics, 11, pages: 8, 2017 (article)

link (url) DOI [BibTex]

al Der, R., Martius, G. Self-Organized Behavior Generation for Musculoskeletal Robots Frontiers in Neurorobotics, 11, pages: 8, 2017 (article)

link (url) DOI [BibTex]

Data-Driven Physics for Human Soft Tissue Animation

Kim, M., Pons-Moll, G., Pujades, S., Bang, S., Kim, J., Black, M. J., Lee, S.

ACM Transactions on Graphics, (Proc. SIGGRAPH), 36(4):54:1-54:12, 2017 (article)

Abstract

Data driven models of human poses and soft-tissue deformations can produce very realistic results, but they only model the visible surface of the human body and cannot create skin deformation due to interactions with the environment. Physical simulations can generalize to external forces, but their parameters are difficult to control. In this paper, we present a layered volumetric human body model learned from data. Our model is composed of a data-driven inner layer and a physics-based external layer. The inner layer is driven with a volumetric statistical body model (VSMPL). The soft tissue layer consists of a tetrahedral mesh that is driven using the finite element method (FEM). Model parameters, namely the segmentation of the body into layers and the soft tissue elasticity, are learned directly from 4D registrations of humans exhibiting soft tissue deformations. The learned two layer model is a realistic full-body avatar that generalizes to novel motions and external forces. Experiments show that the resulting avatars produce realistic results on held out sequences and react to external forces. Moreover, the model supports the retargeting of physical properties from one avatar when they share the same topology.

video paper link (url) Project Page [BibTex]

ps Kim, M., Pons-Moll, G., Pujades, S., Bang, S., Kim, J., Black, M. J., Lee, S. Data-Driven Physics for Human Soft Tissue Animation ACM Transactions on Graphics, (Proc. SIGGRAPH), 36(4):54:1-54:12, 2017 (article)

video paper link (url) Project Page [BibTex]

Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs

(Best Paper, Eurographics 2017)

Marcard, T. V., Rosenhahn, B., Black, M., Pons-Moll, G.

Computer Graphics Forum 36(2), Proceedings of the 38th Annual Conference of the European Association for Computer Graphics (Eurographics), pages: 349-360 , 2017 (article)

Abstract

We address the problem of making human motion capture in the wild more practical by using a small set of inertial sensors attached to the body. Since the problem is heavily under-constrained, previous methods either use a large number of sensors, which is intrusive, or they require additional video input. We take a different approach and constrain the problem by: (i) making use of a realistic statistical body model that includes anthropometric constraints and (ii) using a joint optimization framework to fit the model to orientation and acceleration measurements over multiple frames. The resulting tracker Sparse Inertial Poser (SIP) enables motion capture using only 6 sensors (attached to the wrists, lower legs, back and head) and works for arbitrary human motions. Experiments on the recently released TNT15 dataset show that, using the same number of sensors, SIP achieves higher accuracy than the dataset baseline without using any video data. We further demonstrate the effectiveness of SIP on newly recorded challenging motions in outdoor scenarios such as climbing or jumping over a wall

video pdf Project Page [BibTex]

ps Marcard, T. V., Rosenhahn, B., Black, M., Pons-Moll, G. Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs Computer Graphics Forum 36(2), Proceedings of the 38th Annual Conference of the European Association for Computer Graphics (Eurographics), pages: 349-360 , 2017 (article)

video pdf Project Page [BibTex]

Efficient 2D and 3D Facade Segmentation using Auto-Context

Gadde, R., Jampani, V., Marlet, R., Gehler, P.

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017 (article)

Abstract

This paper introduces a fast and efficient segmentation technique for 2D images and 3D point clouds of building facades. Facades of buildings are highly structured and consequently most methods that have been proposed for this problem aim to make use of this strong prior information. Contrary to most prior work, we are describing a system that is almost domain independent and consists of standard segmentation methods. We train a sequence of boosted decision trees using auto-context features. This is learned using stacked generalization. We find that this technique performs better, or comparable with all previous published methods and present empirical results on all available 2D and 3D facade benchmark datasets. The proposed method is simple to implement, easy to extend, and very efficient at test-time inference.

ps Gadde, R., Jampani, V., Marlet, R., Gehler, P. Efficient 2D and 3D Facade Segmentation using Auto-Context IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017 (article)

video project_page paper link (url) DOI Project Page Project Page [BibTex]

ClothCap: Seamless 4D Clothing Capture and Retargeting

Pons-Moll, G., Pujades, S., Hu, S., Black, M.

ACM Transactions on Graphics, (Proc. SIGGRAPH), 36(4):73:1-73:15, ACM, New York, NY, USA, 2017, Two first authors contributed equally (article)

Abstract

Designing and simulating realistic clothing is challenging and, while several methods have addressed the capture of clothing from 3D scans, previous methods have been limited to single garments and simple motions, lack detail, or require specialized texture patterns. Here we address the problem of capturing regular clothing on fully dressed people in motion. People typically wear multiple pieces of clothing at a time. To estimate the shape of such clothing, track it over time, and render it believably, each garment must be segmented from the others and the body. Our ClothCap approach uses a new multi-part 3D model of clothed bodies, automatically segments each piece of clothing, estimates the naked body shape and pose under the clothing, and tracks the 3D deformations of the clothing over time. We estimate the garments and their motion from 4D scans; that is, high-resolution 3D scans of the subject in motion at 60 fps. The model allows us to capture a clothed person in motion, extract their clothing, and retarget the clothing to new body shapes. ClothCap provides a step towards virtual try-on with a technology for capturing, modeling, and analyzing clothing in motion.

ps Pons-Moll, G., Pujades, S., Hu, S., Black, M. ClothCap: Seamless 4D Clothing Capture and Retargeting ACM Transactions on Graphics, (Proc. SIGGRAPH), 36(4):73:1-73:15, ACM, New York, NY, USA, 2017, Two first authors contributed equally (article)

video project_page paper link (url) DOI Project Page Project Page [BibTex]

Towards Accurate Marker-less Human Shape and Pose Estimation over Time

Huang, Y., Bogo, F., Lassner, C., Kanazawa, A., Gehler, P. V., Romero, J., Akhter, I., Black, M. J.

In International Conference on 3D Vision (3DV), pages: 421-430, 2017 (inproceedings)

Abstract

Existing markerless motion capture methods often assume known backgrounds, static cameras, and sequence specific motion priors, limiting their application scenarios. Here we present a fully automatic method that, given multiview videos, estimates 3D human pose and body shape. We take the recently proposed SMPLify method [12] as the base method and extend it in several ways. First we fit a 3D human body model to 2D features detected in multi-view images. Second, we use a CNN method to segment the person in each image and fit the 3D body model to the contours, further improving accuracy. Third we utilize a generic and robust DCT temporal prior to handle the left and right side swapping issue sometimes introduced by the 2D pose estimator. Validation on standard benchmarks shows our results are comparable to the state of the art and also provide a realistic 3D shape avatar. We also demonstrate accurate results on HumanEva and on challenging monocular sequences of dancing from YouTube.

Code pdf DOI Project Page [BibTex]

ps Huang, Y., Bogo, F., Lassner, C., Kanazawa, A., Gehler, P. V., Romero, J., Akhter, I., Black, M. J. Towards Accurate Marker-less Human Shape and Pose Estimation over Time In International Conference on 3D Vision (3DV), pages: 421-430, 2017 (inproceedings)

Code pdf DOI Project Page [BibTex]

Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art

Janai, J., Güney, F., Behl, A., Geiger, A.

Arxiv, 2017 (article)

Abstract

Recent years have witnessed amazing progress in AI related fields such as computer vision, machine learning and autonomous vehicles. As with any rapidly growing field, however, it becomes increasingly difficult to stay up-to-date or enter the field as a beginner. While several topic specific survey papers have been written, to date no general survey on problems, datasets and methods in computer vision for autonomous vehicles exists. This paper attempts to narrow this gap by providing a state-of-the-art survey on this topic. Our survey includes both the historically most relevant literature as well as the current state-of-the-art on several specific topics, including recognition, reconstruction, motion estimation, tracking, scene understanding and end-to-end learning. Towards this goal, we first provide a taxonomy to classify each approach and then analyze the performance of the state-of-the-art on several challenging benchmarking datasets including KITTI, ISPRS, MOT and Cityscapes. Besides, we discuss open problems and current research challenges. To ease accessibility and accommodate missing references, we will also provide an interactive platform which allows to navigate topics and methods, and provides additional information and project links for each paper.

avg

pdf Project Page Project Page [BibTex]

avg Janai, J., Güney, F., Behl, A., Geiger, A. Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art Arxiv, 2017 (article)

pdf Project Page Project Page [BibTex]

2005

Representing cyclic human motion using functional analysis

Ormoneit, D., Black, M. J., Hastie, T., Kjellström, H.

Image and Vision Computing, 23(14):1264-1276, December 2005 (article)

Abstract

We present a robust automatic method for modeling cyclic 3D human motion such as walking using motion-capture data. The pose of the body is represented by a time-series of joint angles which are automatically segmented into a sequence of motion cycles. The mean and the principal components of these cycles are computed using a new algorithm that enforces smooth transitions between the cycles by operating in the Fourier domain. Key to this method is its ability to automatically deal with noise and missing data. A learned walking model is then exploited for Bayesian tracking of 3D human motion.

pdf pdf from publisher DOI [BibTex]

2005

ps Ormoneit, D., Black, M. J., Hastie, T., Kjellström, H. Representing cyclic human motion using functional analysis Image and Vision Computing, 23(14):1264-1276, December 2005 (article)

pdf pdf from publisher DOI [BibTex]

A quantitative evaluation of video-based 3D person tracking

Balan, A. O., Sigal, L., Black, M. J.

In The Second Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, VS-PETS, pages: 349-356, October 2005 (inproceedings)

ps Balan, A. O., Sigal, L., Black, M. J. A quantitative evaluation of video-based 3D person tracking In The Second Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, VS-PETS, pages: 349-356, October 2005 (inproceedings)

Inferring attentional state and kinematics from motor cortical firing rates

Wood, F., Prabhat, , Donoghue, J. P., Black, M. J.

In Proc. IEEE Engineering in Medicine and Biology Society, pages: 1544-1547, September 2005 (inproceedings)

ps Wood, F., Prabhat, , Donoghue, J. P., Black, M. J. Inferring attentional state and kinematics from motor cortical firing rates In Proc. IEEE Engineering in Medicine and Biology Society, pages: 1544-1547, September 2005 (inproceedings)

Motor cortical decoding using an autoregressive moving average model

Fisher, J., Black, M. J.

In Proc. IEEE Engineering in Medicine and Biology Society, pages: 1469-1472, September 2005 (inproceedings)

ps Fisher, J., Black, M. J. Motor cortical decoding using an autoregressive moving average model In Proc. IEEE Engineering in Medicine and Biology Society, pages: 1469-1472, September 2005 (inproceedings)