ActiveZero++: Mixed Domain Learning Stereo and Confidence-Based Depth Completion With Zero Annotation-Reference-Cited by-同舟云学术

ActiveZero++: Mixed Domain Learning Stereo and Confidence-Based Depth Completion With Zero Annotation

Published:2023-12 Issue:12 Volume:45 Page:14098-14113
ISSN:0162-8828
Container-title:IEEE Transactions on Pattern Analysis and Machine Intelligence
language:
Short-container-title:IEEE Trans. Pattern Anal. Mach. Intell.

Author:

Chen Rui¹^ORCID,Liu Isabella²^ORCID,Yang Edward²^ORCID,Tao Jianyu²^ORCID,Zhang Xiaoshuai²^ORCID,Ran Qing³^ORCID,Liu Zhu⁴^ORCID,Xu Jing¹^ORCID,Su Hao²^ORCID

Affiliation:

1. Department of Mechanical Engineering, State Key Laboratory of Tribology, Beijing Key Laboratory of Precision/Ultra-Precision Manufacturing Equipment Control, Tsinghua University, Beijing, China

2. Department of Computer Science and Engineering, University of California, La Jolla, CA, USA

3. Alibaba DAMO Academy, Hangzhou, China

4. Amazon, Seattle, WA, USA

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software

Link

http://xplorestaging.ieee.org/ielx7/34/10308548/10219021.pdf?arnumber=10219021

Reference59 articles.

1. StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching

2. CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching

3. Self-supervised learning for stereo matching with self-improving ability;zhong,2017

4. Non-parametric local transforms for computing visual correspondence

5. Clear Grasp: 3D Shape Estimation of Transparent Objects for Manipulation

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Robust depth completion based on Semantic Aggregation;Applied Intelligence;2024-03