Header logo is


2018


On the Integration of Optical Flow and Action Recognition
On the Integration of Optical Flow and Action Recognition

Sevilla-Lara, L., Liao, Y., Güney, F., Jampani, V., Geiger, A., Black, M. J.

In German Conference on Pattern Recognition (GCPR), LNCS 11269, pages: 281-297, Springer, Cham, October 2018 (inproceedings)

Abstract
Most of the top performing action recognition methods use optical flow as a "black box" input. Here we take a deeper look at the combination of flow and action recognition, and investigate why optical flow is helpful, what makes a flow method good for action recognition, and how we can make it better. In particular, we investigate the impact of different flow algorithms and input transformations to better understand how these affect a state-of-the-art action recognition method. Furthermore, we fine tune two neural-network flow methods end-to-end on the most widely used action recognition dataset (UCF101). Based on these experiments, we make the following five observations: 1) optical flow is useful for action recognition because it is invariant to appearance, 2) optical flow methods are optimized to minimize end-point-error (EPE), but the EPE of current methods is not well correlated with action recognition performance, 3) for the flow methods tested, accuracy at boundaries and at small displacements is most correlated with action recognition performance, 4) training optical flow to minimize classification error instead of minimizing EPE improves recognition performance, and 5) optical flow learned for the task of action recognition differs from traditional optical flow especially inside the human body and at the boundary of the body. These observations may encourage optical flow researchers to look beyond EPE as a goal and guide action recognition researchers to seek better motion cues, leading to a tighter integration of the optical flow and action recognition communities.

avg ps

arXiv DOI [BibTex]

2018


arXiv DOI [BibTex]


Towards Robust Visual Odometry with a Multi-Camera System
Towards Robust Visual Odometry with a Multi-Camera System

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

In International Conference on Intelligent Robots and Systems (IROS) 2018, International Conference on Intelligent Robots and Systems, October 2018 (inproceedings)

Abstract
We present a visual odometry (VO) algorithm for a multi-camera system and robust operation in challenging environments. Our algorithm consists of a pose tracker and a local mapper. The tracker estimates the current pose by minimizing photometric errors between the most recent keyframe and the current frame. The mapper initializes the depths of all sampled feature points using plane-sweeping stereo. To reduce pose drift, a sliding window optimizer is used to refine poses and structure jointly. Our formulation is flexible enough to support an arbitrary number of stereo cameras. We evaluate our algorithm thoroughly on five datasets. The datasets were captured in different conditions: daytime, night-time with near-infrared (NIR) illumination and night-time without NIR illumination. Experimental results show that a multi-camera setup makes the VO more robust to challenging environments, especially night-time conditions, in which a single stereo configuration fails easily due to the lack of features.

avg

pdf Project Page [BibTex]

pdf Project Page [BibTex]


Learning Priors for Semantic 3D Reconstruction
Learning Priors for Semantic 3D Reconstruction

Cherabier, I., Schönberger, J., Oswald, M., Pollefeys, M., Geiger, A.

In Computer Vision – ECCV 2018, Springer International Publishing, Cham, September 2018 (inproceedings)

Abstract
We present a novel semantic 3D reconstruction framework which embeds variational regularization into a neural network. Our network performs a fixed number of unrolled multi-scale optimization iterations with shared interaction weights. In contrast to existing variational methods for semantic 3D reconstruction, our model is end-to-end trainable and captures more complex dependencies between the semantic labels and the 3D geometry. Compared to previous learning-based approaches to 3D reconstruction, we integrate powerful long-range dependencies using variational coarse-to-fine optimization. As a result, our network architecture requires only a moderate number of parameters while keeping a high level of expressiveness which enables learning from very little data. Experiments on real and synthetic datasets demonstrate that our network achieves higher accuracy compared to a purely variational approach while at the same time requiring two orders of magnitude less iterations to converge. Moreover, our approach handles ten times more semantic class labels using the same computational resources.

avg

pdf suppmat Project Page Video DOI Project Page [BibTex]

pdf suppmat Project Page Video DOI Project Page [BibTex]


Unsupervised Learning of Multi-Frame Optical Flow with Occlusions
Unsupervised Learning of Multi-Frame Optical Flow with Occlusions

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

In European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, vol 11220, pages: 713-731, Springer, Cham, September 2018 (inproceedings)

avg ps

pdf suppmat Video Project Page DOI Project Page [BibTex]

pdf suppmat Video Project Page DOI Project Page [BibTex]


SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images
SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images

Coors, B., Condurache, A. P., Geiger, A.

European Conference on Computer Vision (ECCV), September 2018 (conference)

Abstract
Omnidirectional cameras offer great benefits over classical cameras wherever a wide field of view is essential, such as in virtual reality applications or in autonomous robots. Unfortunately, standard convolutional neural networks are not well suited for this scenario as the natural projection surface is a sphere which cannot be unwrapped to a plane without introducing significant distortions, particularly in the polar regions. In this work, we present SphereNet, a novel deep learning framework which encodes invariance against such distortions explicitly into convolutional neural networks. Towards this goal, SphereNet adapts the sampling locations of the convolutional filters, effectively reversing distortions, and wraps the filters around the sphere. By building on regular convolutions, SphereNet enables the transfer of existing perspective convolutional neural network models to the omnidirectional case. We demonstrate the effectiveness of our method on the tasks of image classification and object detection, exploiting two newly created semi-synthetic and real-world omnidirectional datasets.

avg

pdf suppmat Project Page [BibTex]


Robust Dense Mapping for Large-Scale Dynamic Environments
Robust Dense Mapping for Large-Scale Dynamic Environments

Barsan, I. A., Liu, P., Pollefeys, M., Geiger, A.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2018, IEEE, International Conference on Robotics and Automation, May 2018 (inproceedings)

Abstract
We present a stereo-based dense mapping algorithm for large-scale dynamic urban environments. In contrast to other existing methods, we simultaneously reconstruct the static background, the moving objects, and the potentially moving but currently stationary objects separately, which is desirable for high-level mobile robotic tasks such as path planning in crowded environments. We use both instance-aware semantic segmentation and sparse scene flow to classify objects as either background, moving, or potentially moving, thereby ensuring that the system is able to model objects with the potential to transition from static to dynamic, such as parked cars. Given camera poses estimated from visual odometry, both the background and the (potentially) moving objects are reconstructed separately by fusing the depth maps computed from the stereo input. In addition to visual odometry, sparse scene flow is also used to estimate the 3D motions of the detected moving objects, in order to reconstruct them accurately. A map pruning technique is further developed to improve reconstruction accuracy and reduce memory consumption, leading to increased scalability. We evaluate our system thoroughly on the well-known KITTI dataset. Our system is capable of running on a PC at approximately 2.5Hz, with the primary bottleneck being the instance-aware semantic segmentation, which is a limitation we hope to address in future work.

avg

pdf Video Project Page Project Page [BibTex]

pdf Video Project Page Project Page [BibTex]


no image
Haptics and Haptic Interfaces

Kuchenbecker, K. J.

In Encyclopedia of Robotics, (Editors: Marcelo H. Ang and Oussama Khatib and Bruno Siciliano), Springer, May 2018 (incollection)

Abstract
Haptics is an interdisciplinary field that seeks to both understand and engineer touch-based interaction. Although a wide range of systems and applications are being investigated, haptics researchers often concentrate on perception and manipulation through the human hand. A haptic interface is a mechatronic system that modulates the physical interaction between a human and his or her tangible surroundings. Haptic interfaces typically involve mechanical, electrical, and computational layers that work together to sense user motions or forces, quickly process these inputs with other information, and physically respond by actuating elements of the user’s surroundings, thereby enabling him or her to act on and feel a remote and/or virtual environment.

hi

link (url) DOI [BibTex]

link (url) DOI [BibTex]


RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials
RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials

Paschalidou, D., Ulusoy, A. O., Schmitt, C., Gool, L., Geiger, A.

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2018, 2018 (inproceedings)

Abstract
In this paper, we consider the problem of reconstructing a dense 3D model using images captured from different views. Recent methods based on convolutional neural networks (CNN) allow learning the entire task from data. However, they do not incorporate the physics of image formation such as perspective geometry and occlusion. Instead, classical approaches based on Markov Random Fields (MRF) with ray-potentials explicitly model these physical processes, but they cannot cope with large surface appearance variations across different viewpoints. In this paper, we propose RayNet, which combines the strengths of both frameworks. RayNet integrates a CNN that learns view-invariant feature representations with an MRF that explicitly encodes the physics of perspective projection and occlusion. We train RayNet end-to-end using empirical risk minimization. We thoroughly evaluate our approach on challenging real-world datasets and demonstrate its benefits over a piece-wise trained baseline, hand-crafted models as well as other learning-based approaches.

avg

pdf suppmat Video Project Page code Poster Project Page [BibTex]

pdf suppmat Video Project Page code Poster Project Page [BibTex]


no image
Travelling Ultrasonic Wave Enhances Keyclick Sensation

Gueorguiev, D., Kaci, A., Amberg, M., Giraud, F., Lemaire-Semail, B.

In Haptics: Science, Technology, and Applications, pages: 302-312, Springer International Publishing, Cham, 2018 (inproceedings)

Abstract
A realistic keyclick sensation is a serious challenge for haptic feedback since vibrotactile rendering faces the limitation of the absence of contact force as experienced on physical buttons. It has been shown that creating a keyclick sensation is possible with stepwise ultrasonic friction modulation. However, the intensity of the sensation is limited by the impedance of the fingertip and by the absence of a lateral force component external to the finger. In our study, we compare this technique to rendering with an ultrasonic travelling wave, which exerts a lateral force on the fingertip. For both techniques, participants were asked to report the detection (or not) of a keyclick during a forced choice one interval procedure. In experiment 1, participants could press the surface as many time as they wanted for a given trial. In experiment 2, they were constrained to press only once. The results show a lower perceptual threshold for travelling waves. Moreover, participants pressed less times per trial and exerted smaller normal force on the surface. The subjective quality of the sensation was found similar for both techniques. In general, haptic feedback based on travelling ultrasonic waves is promising for applications without lateral motion of the finger.

hi

[BibTex]

[BibTex]


Deep Marching Cubes: Learning Explicit Surface Representations
Deep Marching Cubes: Learning Explicit Surface Representations

Liao, Y., Donne, S., Geiger, A.

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2018, 2018 (inproceedings)

Abstract
Existing learning based solutions to 3D surface prediction cannot be trained end-to-end as they operate on intermediate representations (eg, TSDF) from which 3D surface meshes must be extracted in a post-processing step (eg, via the marching cubes algorithm). In this paper, we investigate the problem of end-to-end 3D surface prediction. We first demonstrate that the marching cubes algorithm is not differentiable and propose an alternative differentiable formulation which we insert as a final layer into a 3D convolutional neural network. We further propose a set of loss functions which allow for training our model with sparse point supervision. Our experiments demonstrate that the model allows for predicting sub-voxel accurate 3D shapes of arbitrary topology. Additionally, it learns to complete shapes and to separate an object's inside from its outside even in the presence of sparse and incomplete ground truth. We investigate the benefits of our approach on the task of inferring shapes from 3D point clouds. Our model is flexible and can be combined with a variety of shape encoder and shape inference techniques.

avg

pdf suppmat Video Project Page Poster Project Page [BibTex]

pdf suppmat Video Project Page Poster Project Page [BibTex]


Semantic Visual Localization
Semantic Visual Localization

Schönberger, J., Pollefeys, M., Geiger, A., Sattler, T.

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2018, 2018 (inproceedings)

Abstract
Robust visual localization under a wide range of viewing conditions is a fundamental problem in computer vision. Handling the difficult cases of this problem is not only very challenging but also of high practical relevance, eg, in the context of life-long localization for augmented reality or autonomous robots. In this paper, we propose a novel approach based on a joint 3D geometric and semantic understanding of the world, enabling it to succeed under conditions where previous approaches failed. Our method leverages a novel generative model for descriptor learning, trained on semantic scene completion as an auxiliary task. The resulting 3D descriptors are robust to missing observations by encoding high-level 3D geometric and semantic information. Experiments on several challenging large-scale localization datasets demonstrate reliable localization under extreme viewpoint, illumination, and geometry changes.

avg

pdf suppmat Poster Project Page [BibTex]

pdf suppmat Poster Project Page [BibTex]


no image
Exploring Fingers’ Limitation of Texture Density Perception on Ultrasonic Haptic Displays

Kalantari, F., Gueorguiev, D., Lank, E., Bremard, N., Grisoni, L.

In Haptics: Science, Technology, and Applications, pages: 354-365, Springer International Publishing, Cham, 2018 (inproceedings)

Abstract
Recent research in haptic feedback is motivated by the crucial role that tactile perception plays in everyday touch interactions. In this paper, we describe psychophysical experiments to investigate the perceptual threshold of individual fingers on both the right and left hand of right-handed participants using active dynamic touch for spatial period discrimination of both sinusoidal and square-wave gratings on ultrasonic haptic touchscreens. Both one-finger and multi-finger touch were studied and compared. Our results indicate that users' finger identity (index finger, middle finger, etc.) significantly affect the perception of both gratings in the case of one-finger exploration. We show that index finger and thumb are the most sensitive in all conditions whereas little finger followed by ring are the least sensitive for haptic perception. For multi-finger exploration, the right hand was found to be more sensitive than the left hand for both gratings. Our findings also demonstrate similar perception sensitivity between multi-finger exploration and the index finger of users' right hands (i.e. dominant hand in our study), while significant difference was found between single and multi-finger perception sensitivity for the left hand.

hi

[BibTex]

[BibTex]


Which Training Methods for GANs do actually Converge?
Which Training Methods for GANs do actually Converge?

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

International Conference on Machine learning (ICML), 2018 (conference)

Abstract
Recent work has shown local convergence of GAN training for absolutely continuous data and generator distributions. In this paper, we show that the requirement of absolute continuity is necessary: we describe a simple yet prototypical counterexample showing that in the more realistic case of distributions that are not absolutely continuous, unregularized GAN training is not always convergent. Furthermore, we discuss regularization strategies that were recently proposed to stabilize GAN training. Our analysis shows that GAN training with instance noise or zero-centered gradient penalties converges. On the other hand, we show that Wasserstein-GANs and WGAN-GP with a finite number of discriminator updates per generator update do not always converge to the equilibrium point. We discuss these results, leading us to a new explanation for the stability problems of GAN training. Based on our analysis, we extend our convergence results to more general GANs and prove local convergence for simplified gradient penalties even if the generator and data distributions lie on lower dimensional manifolds. We find these penalties to work well in practice and use them to learn high-resolution generative image models for a variety of datasets with little hyperparameter tuning.

avg

code video paper supplement slides poster Project Page [BibTex]


Learning 3D Shape Completion from Laser Scan Data with Weak Supervision
Learning 3D Shape Completion from Laser Scan Data with Weak Supervision

Stutz, D., Geiger, A.

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2018, 2018 (inproceedings)

Abstract
3D shape completion from partial point clouds is a fundamental problem in computer vision and computer graphics. Recent approaches can be characterized as either data-driven or learning-based. Data-driven approaches rely on a shape model whose parameters are optimized to fit the observations. Learning-based approaches, in contrast, avoid the expensive optimization step and instead directly predict the complete shape from the incomplete observations using deep neural networks. However, full supervision is required which is often not available in practice. In this work, we propose a weakly-supervised learning-based approach to 3D shape completion which neither requires slow optimization nor direct supervision. While we also learn a shape prior on synthetic data, we amortize, ie, learn, maximum likelihood fitting using deep neural networks resulting in efficient shape completion without sacrificing accuracy. Tackling 3D shape completion of cars on ShapeNet and KITTI, we demonstrate that the proposed amortized maximum likelihood approach is able to compete with a fully supervised baseline and a state-of-the-art data-driven approach while being significantly faster. On ModelNet, we additionally show that the approach is able to generalize to other object categories as well.

avg

pdf suppmat Project Page Poster Project Page [BibTex]

pdf suppmat Project Page Poster Project Page [BibTex]


Learning Transformation Invariant Representations with Weak Supervision
Learning Transformation Invariant Representations with Weak Supervision

Coors, B., Condurache, A., Mertins, A., Geiger, A.

In International Conference on Computer Vision Theory and Applications, International Conference on Computer Vision Theory and Applications, 2018 (inproceedings)

Abstract
Deep convolutional neural networks are the current state-of-the-art solution to many computer vision tasks. However, their ability to handle large global and local image transformations is limited. Consequently, extensive data augmentation is often utilized to incorporate prior knowledge about desired invariances to geometric transformations such as rotations or scale changes. In this work, we combine data augmentation with an unsupervised loss which enforces similarity between the predictions of augmented copies of an input sample. Our loss acts as an effective regularizer which facilitates the learning of transformation invariant representations. We investigate the effectiveness of the proposed similarity loss on rotated MNIST and the German Traffic Sign Recognition Benchmark (GTSRB) in the context of different classification models including ladder networks. Our experiments demonstrate improvements with respect to the standard data augmentation approach for supervised and semi-supervised learning tasks, in particular in the presence of little annotated data. In addition, we analyze the performance of the proposed approach with respect to its hyperparameters, including the strength of the regularization as well as the layer where representation similarity is enforced.

avg

pdf [BibTex]

pdf [BibTex]

2016


no image
Qualitative User Reactions to a Hand-Clapping Humanoid Robot

Fitter, N. T., Kuchenbecker, K. J.

In Social Robotics: 8th International Conference, ICSR 2016, Kansas City, MO, USA, November 1-3, 2016 Proceedings, 9979, pages: 317-327, Lecture Notes in Artificial Intelligence, Springer International Publishing, November 2016, Oral presentation given by Fitter (inproceedings)

hi

[BibTex]

2016


[BibTex]


no image
Designing and Assessing Expressive Open-Source Faces for the Baxter Robot

Fitter, N. T., Kuchenbecker, K. J.

In Social Robotics: 8th International Conference, ICSR 2016, Kansas City, MO, USA, November 1-3, 2016 Proceedings, 9979, pages: 340-350, Lecture Notes in Artificial Intelligence, Springer International Publishing, November 2016, Oral presentation given by Fitter (inproceedings)

hi

[BibTex]

[BibTex]


no image
Rhythmic Timing in Playful Human-Robot Social Motor Coordination

Fitter, N. T., Hawkes, D. T., Kuchenbecker, K. J.

In Social Robotics: 8th International Conference, ICSR 2016, Kansas City, MO, USA, November 1-3, 2016 Proceedings, 9979, pages: 296-305, Lecture Notes in Artificial Intelligence, Springer International Publishing, November 2016, Oral presentation given by Fitter (inproceedings)

hi

[BibTex]

[BibTex]


no image
Using IMU Data to Demonstrate Hand-Clapping Games to a Robot

Fitter, N. T., Kuchenbecker, K. J.

In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 851 - 856, October 2016, Interactive presentation given by Fitter (inproceedings)

hi

[BibTex]

[BibTex]


no image
ProtonPack: A Visuo-Haptic Data Acquisition System for Robotic Learning of Surface Properties

Burka, A., Hu, S., Helgeson, S., Krishnan, S., Gao, Y., Hendricks, L. A., Darrell, T., Kuchenbecker, K. J.

In Proceedings of the IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), pages: 58-65, 2016, Oral presentation given by Burka (inproceedings)

hi

Project Page [BibTex]

Project Page [BibTex]


no image
Equipping the Baxter Robot with Human-Inspired Hand-Clapping Skills

Fitter, N. T., Kuchenbecker, K. J.

In Proceedings of the IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), pages: 105-112, 2016 (inproceedings)

hi

[BibTex]

[BibTex]


no image
Comparison of vibro-acoustic performance metrics in the design and optimization of stiffened composite fuselages

Serhat, G., Basdogan, I.

In Proceedings of International Congress and Exposition of Noise Control Engineering (INTER-NOISE), Hamburg, Germany, August 2016 (inproceedings)

Abstract
In this paper, a comparison of preliminary design methodologies for optimization of stiffened, fiber-reinforced composite fuselages for vibro-acoustic requirements is presented. Fuselage stiffness properties are modelled using lamination parameters and their effect on the vibro-acoustic performance is investigated using two different approaches. First method, only considers the structural model in order to explore the effect of design variables on fuselage vibrations. The simplified estimation of the acoustic behavior without considering fluid-structure interaction brings certain advantages such as reduced modelling effort and computational cost. In this case, the performance metric is chosen as equivalent radiated power (ERP) which is a well-known criterion in the prediction of structure-born noise. Second method, utilizes coupled vibro-acoustic models to predict the sound pressure levels (SPL) inside the fuselage. ERP is calculated both for bay panels and fuselage section and then compared with the SPL results. The response surfaces of each metric are determined as a function of lamination parameters and their overall difference is quantified. ERP approach proves its merit provided that a sufficiently accurate model is used. The results demonstrate the importance of the simplifications made in the modelling and the selection of analysis approach in vibro-acoustic design of fuselages.

hi

[BibTex]

[BibTex]


no image
Reproducing a Laser Pointer Dot on a Secondary Projected Screen

Hu, S., Kuchenbecker, K. J.

In Proceedings of the IEEE International Conference on Advanced Intelligent Mechatronics (AIM), pages: 1645-1650, 2016, Oral presentation given by Hu (inproceedings)

hi

[BibTex]

[BibTex]


no image
Effect of Aspect Ratio and Boundary Conditions on the Eigenfrequency Optimization of Composite Panels Using Lamination Parameters

Serhat, G., Basdogan, I.

In Proceedings of the ASMO UK International Conference on Numerical Optimisation Methods for Engineering Design, pages: 160–168, Munich, Germany, July 2016 (inproceedings)

Abstract
Eigenfrequency optimization of laminated composite panels is a common engineering problem. This process mostly involves designing stiffness properties of the structure. Optimal results can differ significantly depending on the values of the model parameters and the metrics used for the optimization. Building the know-how on this matter is crucial for choosing the appropriate design methodologies as well as validation and justification of prospective results. In this paper, effects of aspect ratio and boundary conditions on eigenfrequency optimization of composite panels by altering stiffness properties are investigated. Lamination parameters are chosen as design variables which are used in the modeling of stiffness tensors. This technique enables representation of overall stiffness characteristics and provides a convex design space. Fundamental frequency and difference between fundamental and second natural frequencies are maximized as design objectives. Optimization studies incorporating different models and responses are performed. Optimal lamination parameters and response values are provided for each case and the effects of model parameters on the solutions are quantified. The results indicate that trends of the optima change for different aspect ratio ranges and boundary conditions. Moreover, convergence occurs beyond certain critical values of the model parameters which may cause an optimization study to be redundant.

hi

[BibTex]

[BibTex]


Patches, Planes and Probabilities: A Non-local Prior for Volumetric {3D} Reconstruction
Patches, Planes and Probabilities: A Non-local Prior for Volumetric 3D Reconstruction

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

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2016 (inproceedings)

Abstract
In this paper, we propose a non-local structured prior for volumetric multi-view 3D reconstruction. Towards this goal, we present a novel Markov random field model based on ray potentials in which assumptions about large 3D surface patches such as planarity or Manhattan world constraints can be efficiently encoded as probabilistic priors. We further derive an inference algorithm that reasons jointly about voxels, pixels and image segments, and estimates marginal distributions of appearance, occupancy, depth, normals and planarity. Key to tractable inference is a novel hybrid representation that spans both voxel and pixel space and that integrates non-local information from 2D image segmentations in a principled way. We compare our non-local prior to commonly employed local smoothness assumptions and a variety of state-of-the-art volumetric reconstruction baselines on challenging outdoor scenes with textureless and reflective surfaces. Our experiments indicate that regularizing over larger distances has the potential to resolve ambiguities where local regularizers fail.

avg ps

YouTube pdf poster suppmat Project Page [BibTex]

YouTube pdf poster suppmat Project Page [BibTex]


no image
Multi-objective optimization of stiffened, fiber-reinforced composite fuselages for mechanical and vibro-acoustic requirements

Serhat, G., Faria, T. G., Basdogan, I.

In Proceedings of AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, Washington, USA, June 2016 (inproceedings)

Abstract
In this paper, a preliminary design methodology for optimization of stiffened, fiber-reinforced composite fuselages for combined mechanical and vibro-acoustic requirements is presented. Laminate stiffness distributions are represented using the method called lamination parameters which is known to provide a convex solution space. Single-objective and multi-objective optimization studies are carried out in order to find optimal stiffness distributions. Performance metrics for acoustical behavior are chosen as maximum fundamental frequency and minimum equivalent radiated power. The mechanical performance metric is chosen as the maximum stiffness. The results show that the presented methodology works effectively and it can be used to improve load-carrying and acoustical performances simultaneously.

hi

DOI [BibTex]

DOI [BibTex]


Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer
Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer

Xie, J., Kiefel, M., Sun, M., Geiger, A.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2016 (inproceedings)

Abstract
Semantic annotations are vital for training models for object recognition, semantic segmentation or scene understanding. Unfortunately, pixelwise annotation of images at very large scale is labor-intensive and only little labeled data is available, particularly at instance level and for street scenes. In this paper, we propose to tackle this problem by lifting the semantic instance labeling task from 2D into 3D. Given reconstructions from stereo or laser data, we annotate static 3D scene elements with rough bounding primitives and develop a probabilistic model which transfers this information into the image domain. We leverage our method to obtain 2D labels for a novel suburban video dataset which we have collected, resulting in 400k semantic and instance image annotations. A comparison of our method to state-of-the-art label transfer baselines reveals that 3D information enables more efficient annotation while at the same time resulting in improved accuracy and time-coherent labels.

avg ps

pdf suppmat Project Page Project Page [BibTex]

pdf suppmat Project Page Project Page [BibTex]


no image
Deep Learning for Tactile Understanding From Visual and Haptic Data

Gao, Y., Hendricks, L. A., Kuchenbecker, K. J., Darrell, T.

In Proceedings of the IEEE International Conference on Robotics and Automation, pages: 536-543, May 2016, Oral presentation given by Gao (inproceedings)

hi

[BibTex]

[BibTex]


no image
Robust Tactile Perception of Artificial Tumors Using Pairwise Comparisons of Sensor Array Readings

Hui, J. C. T., Block, A. E., Taylor, C. J., Kuchenbecker, K. J.

In Proceedings of the IEEE Haptics Symposium, pages: 305-312, Philadelphia, Pennsylvania, USA, April 2016, Oral presentation given by Hui (inproceedings)

hi

[BibTex]

[BibTex]


no image
Data-Driven Comparison of Four Cutaneous Displays for Pinching Palpation in Robotic Surgery

Brown, J. D., Ibrahim, M., Chase, E. D. Z., Pacchierotti, C., Kuchenbecker, K. J.

In Proceedings of the IEEE Haptics Symposium, pages: 147-154, Philadelphia, Pennsylvania, USA, April 2016, Oral presentation given by Brown (inproceedings)

hi

[BibTex]

[BibTex]


Multisensory Robotic Therapy through Motion Capture and Imitation for Children with ASD
Multisensory Robotic Therapy through Motion Capture and Imitation for Children with ASD

Burns, R., Nizambad, S., Park, C. H., Jeon, M., Howard, A.

Proceedings of the American Society of Engineering Education, Mid-Atlantic Section, Spring Conference, April 2016 (conference)

Abstract
It is known that children with autism have difficulty with emotional communication. As the population of children with autism increases, it is crucial we create effective therapeutic programs that will improve their communication skills. We present an interactive robotic system that delivers emotional and social behaviors for multi­sensory therapy for children with autism spectrum disorders. Our framework includes emotion­-based robotic gestures and facial expressions, as well as tracking and understanding the child’s responses through Kinect motion capture.

hi

link (url) [BibTex]

link (url) [BibTex]


no image
Design and Implementation of a Visuo-Haptic Data Acquisition System for Robotic Learning of Surface Properties

Burka, A., Hu, S., Helgeson, S., Krishnan, S., Gao, Y., Hendricks, L. A., Darrell, T., Kuchenbecker, K. J.

In Proceedings of the IEEE Haptics Symposium, pages: 350-352, April 2016, Work-in-progress paper. Poster presentation given by Burka (inproceedings)

hi

Project Page [BibTex]

Project Page [BibTex]


Multisensory robotic therapy to promote natural emotional interaction for children with ASD
Multisensory robotic therapy to promote natural emotional interaction for children with ASD

Burns, R., Azzi, P., Spadafora, M., Park, C. H., Jeon, M., Kim, H. J., Lee, J., Raihan, K., Howard, A.

Proceedings of the Eleventh ACM/IEEE International Conference on Human Robot Interaction (HRI), pages: 571-571, March 2016 (conference)

Abstract
In this video submission, we are introduced to two robots, Romo the penguin and Darwin Mini. We have programmed these robots to perform a variety of emotions through facial expression and body language, respectively. We aim to use these robots with children with autism, to demo safe emotional and social responses in various sensory situations.

hi

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Interactive Robotic Framework for Multi-Sensory Therapy for Children with Autism Spectrum Disorder
Interactive Robotic Framework for Multi-Sensory Therapy for Children with Autism Spectrum Disorder

Burns, R., Park, C. H., Kim, H. J., Lee, J., Rennie, A., Jeon, M., Howard, A.

In Proceedings of the Eleventh ACM/IEEE International Conference on Human Robot Interaction (HRI), pages: 421-422, March 2016 (inproceedings)

Abstract
In this abstract, we present the overarching goal of our interactive robotic framework - to teach emotional and social behavior to children with autism spectrum disorders via multi-sensory therapy. We introduce our robot characters, Romo and Darwin Mini, and the "Five Senses" scenario they will undergo. This sensory game will develop the children's interest, and will model safe and appropriate reactions to typical sensory overload stimuli.

hi

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Deep Discrete Flow
Deep Discrete Flow

Güney, F., Geiger, A.

Asian Conference on Computer Vision (ACCV), 2016 (conference) Accepted

avg ps

pdf suppmat Project Page [BibTex]

pdf suppmat Project Page [BibTex]


no image
Psychophysical Power Optimization of Friction Modulation for Tactile Interfaces

Sednaoui, T., Vezzoli, E., Gueorguiev, D., Amberg, M., Chappaz, C., Lemaire-Semail, B.

In Haptics: Perception, Devices, Control, and Applications, pages: 354-362, Springer International Publishing, Cham, 2016 (inproceedings)

Abstract
Ultrasonic vibration and electrovibration can modulate the friction between a surface and a sliding finger. The power consumption of these devices is critical to their integration in modern mobile devices such as smartphones. This paper presents a simple control solution to reduce up to 68.8 {\%} this power consumption by taking advantage of the human perception limits.

hi

[BibTex]

[BibTex]


Effect of Waveform in Haptic Perception of Electrovibration on Touchscreens
Effect of Waveform in Haptic Perception of Electrovibration on Touchscreens

Vardar, Y., Güçlü, B., Basdogan, C.

In Haptics: Perception, Devices, Control, and Applications, pages: 190-203, Springer International Publishing, Cham, 2016 (inproceedings)

Abstract
The perceived intensity of electrovibration can be altered by modulating the amplitude, frequency, and waveform of the input voltage signal applied to the conductive layer of a touchscreen. Even though the effect of the first two has been already investigated for sinusoidal signals, we are not aware of any detailed study investigating the effect of the waveform on our haptic perception in the domain of electrovibration. This paper investigates how input voltage waveform affects our haptic perception of electrovibration on touchscreens. We conducted absolute detection experiments using square wave and sinusoidal input signals at seven fundamental frequencies (15, 30, 60, 120, 240, 480 and 1920 Hz). Experimental results depicted the well-known U-shaped tactile sensitivity across frequencies. However, the sensory thresholds were lower for the square wave than the sinusoidal wave at fundamental frequencies less than 60 Hz while they were similar at higher frequencies. Using an equivalent circuit model of a finger-touchscreen system, we show that the sensation difference between the waveforms at low fundamental frequencies can be explained by frequency-dependent electrical properties of human skin and the differential sensitivity of mechanoreceptor channels to individual frequency components in the electrostatic force. As a matter of fact, when the electrostatic force waveforms are analyzed in the frequency domain based on human vibrotactile sensitivity data from the literature [15], the electrovibration stimuli caused by square-wave input signals at all the tested frequencies in this study are found to be detected by the Pacinian psychophysical channel.

hi

vardar_eurohaptics_2016 [BibTex]

vardar_eurohaptics_2016 [BibTex]

2005


no image
Perception of Curvature and Object Motion Via Contact Location Feedback

Provancher, W. R., Kuchenbecker, K. J., Niemeyer, G., Cutkosky, M. R.

In Proceedings of the International Symposium on Robotics Research (ISRR), 15, pages: 456-465, Springer Tracts in Advanced Robotics, Springer, Siena, Italy, 2005, Oral presentation given by Provancher in October of 2003 (inproceedings)

hi

[BibTex]

2005


[BibTex]


no image
Modeling Induced Master Motion in Force-Reflecting Teleoperation

Kuchenbecker, K. J., Niemeyer, G.

In Proc. IEEE International Conference on Robotics and Automation, pages: 348-353, Barcelona, Spain, April 2005, Oral presentation given by Kuchenbecker (inproceedings)

hi

[BibTex]

[BibTex]


no image
Event-Based Haptics and Acceleration Matching: Portraying and Assessing the Realism of Contact

Kuchenbecker, K. J., Fiene, J. P., Niemeyer, G.

In Proc. IEEE World Haptics Conference, pages: 381-387, Pisa, Italy, March 2005, Oral presentation given by Kuchenbecker (inproceedings)

hi

[BibTex]

[BibTex]