scholarly journals Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

Author(s):  
Anurag Ranjan ◽  
Varun Jampani ◽  
Lukas Balles ◽  
Kihwan Kim ◽  
Deqing Sun ◽  
...  
Author(s):  
Liang Liu ◽  
Guangyao Zhai ◽  
Wenlong Ye ◽  
Yong Liu

Scene flow estimation in the dynamic scene remains a challenging task. Computing scene flow by a combination of 2D optical flow and depth has shown to be considerably faster with acceptable performance. In this work, we present a unified framework for joint unsupervised learning of stereo depth and optical flow with explicit local rigidity to estimate scene flow. We estimate camera motion directly by a Perspective-n-Point method from the optical flow and depth predictions, with RANSAC outlier rejection scheme. In order to disambiguate the object motion and the camera motion in the scene, we distinguish the rigid region by the re-project error and the photometric similarity. By joint learning with the local rigidity, both depth and optical networks can be refined. This framework boosts all four tasks: depth, optical flow, camera motion estimation, and object motion segmentation. Through the evaluation on the KITTI benchmark, we show that the proposed framework achieves state-of-the-art results amongst unsupervised methods. Our models and code are available at https://github.com/lliuz/unrigidflow.


Author(s):  
Muhammad Zulhilmi Kaharuddin ◽  
Siti Badriah Khairu Razak ◽  
Mohamed Shawal Abd Rahman ◽  
Wee Chang An ◽  
Muhammad Ikram Kushairi ◽  
...  

Author(s):  
Shuaicheng Liu ◽  
Kunming Luo ◽  
Nianjin Ye ◽  
Chuan Wang ◽  
Jue Wanga ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document