Header logo is

Adversarial Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation




We address the unsupervised learning of several interconnected problems in low-level vision: single view depth prediction, camera motion estimation, optical flow and segmentation of a video into the static scene and moving regions. Our key insight is that these four fundamental vision problems are coupled and, consequently, learning to solve them together simplifies the problem because the solutions can reinforce each other by exploiting known geometric constraints. In order to model geometric constraints, we introduce Adversarial Collaboration, a framework that facilitates competition and collaboration between neural networks. We go beyond previous work by exploiting geometry more explicitly and segmenting the scene into static and moving regions. Adversarial Collaboration works much like expectation-maximization but with neural networks that act as adversaries, competing to explain pixels that correspond to static or moving regions, and as collaborators through a moderator that assigns pixels to be either static or independently moving. Our novel method integrates all these problems in a common framework and simultaneously reasons about the segmentation of the scene into moving objects and the static background, the camera motion, depth of the static scene structure, and the optical flow of moving objects. Our model is trained without any supervision and achieves state of the art results amongst unsupervised methods.

Author(s): Anurag Ranjan and Varun Jampani and Kihwan Kim and Deqing Sun and Jonas Wulff and Michael J. Black
Year: 2018
Month: May

Department(s): Perceiving Systems
Research Project(s): Learning Optical Flow
Scene Models for Optical Flow
Bibtex Type: Article (article)
Paper Type: Conference

URL: http://github.com/anuragranj/ac
Attachments: pdf


  title = {Adversarial Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation},
  author = {Ranjan, Anurag and Jampani, Varun and Kim, Kihwan and Sun, Deqing and Wulff, Jonas and Black, Michael J.},
  month = may,
  year = {2018},
  url = {http://github.com/anuragranj/ac},
  month_numeric = {5}