Edward Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Edward Yang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Hao Su
University of California San Diego, San Diego, USA
1 shared publication - Isabella Liu
University of California San Diego, La Jolla, USA
1 shared publication - Jianyu Tao
Department of Computer Science and Engineering, University of California, La Jolla, CA, USA
1 shared publication - Jing Xu
Tsinghua University
1 shared publication - Qing Ran
Alibaba Group, China
1 shared publication - Rui Chen
Department of Mechanical Engineering, Tsinghua University, Beijing, China
1 shared publication
Latest Publications
- 15 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (12) , 14098-14113
ActiveZero++: Mixed Domain Learning Stereo and Confidence-Based Depth Completion With Zero Annotation
Learning-based stereo methods usually require a large scale dataset with depth, however obtaining accurate depth in the real domain is difficult, but groundtruth depth is readily available in the simulation domain. In this article we propose a new framework, ActiveZero++, which is a mixed domain learning solution for active stereovision systems that requires no real world depth annotation. In the simulation domain, we use a combination of supervised disparity loss and self-supervised loss on a shape primitives dataset. By contrast, in the real domain, we only use self-supervised loss on a dataset that is out-of-distribution from either training simulation data or test real data. To improve the robustness and accuracy of our reprojection loss in hard-to-perceive regions, our method introduces a novel self-supervised loss called temporal IR reprojection. Further, we propose the confidence-based depth completion module, which uses the confidence from the stereo network to identify and improve erroneous areas in depth prediction through depth-normal consistency. Extensive qualitative and quantitative evaluations on real-world data demonstrate state-of-the-art results that can even outperform a commercial depth sensor. Furthermore, our method can significantly narrow the Sim2Real domain gap of depth maps for state-of-the-art learning based 6D pose estimation algorithms.
- 15 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (12) , 14098-14113
ActiveZero++: Mixed Domain Learning Stereo and Confidence-Based Depth Completion With Zero Annotation
Learning-based stereo methods usually require a large scale dataset with depth, however obtaining accurate depth in the real domain is difficult, but groundtruth depth is readily available in the simulation domain. In this article we propose a new framework, ActiveZero++, which is a mixed domain learning solution for active stereovision systems that requires no real world depth annotation. In the simulation domain, we use a combination of supervised disparity loss and self-supervised loss on a shape primitives dataset. By contrast, in the real domain, we only use self-supervised loss on a dataset that is out-of-distribution from either training simulation data or test real data. To improve the robustness and accuracy of our reprojection loss in hard-to-perceive regions, our method introduces a novel self-supervised loss called temporal IR reprojection. Further, we propose the confidence-based depth completion module, which uses the confidence from the stereo network to identify and improve erroneous areas in depth prediction through depth-normal consistency. Extensive qualitative and quantitative evaluations on real-world data demonstrate state-of-the-art results that can even outperform a commercial depth sensor. Furthermore, our method can significantly narrow the Sim2Real domain gap of depth maps for state-of-the-art learning based 6D pose estimation algorithms.