18 citations · 44 across the 24 of their papers we have counts for
5 papers · 1 filter
FlowDA: Unsupervised Domain Adaptive Framework for Optical Flow Estimation
Miaojie Feng, Longliang Liu, Hao Jia +2
Collecting real-world optical flow datasets is a formidable challenge due to the high cost of labeling. A shortage of datasets significantly constrains the real-world performance o…
Memory-Efficient Optical Flow via Radius-Distribution Orthogonal Cost Volume
Gangwei Xu, Shujun Chen, Hao Jia +2
The full 4D cost volume in Recurrent All-Pairs Field Transforms (RAFT) or global matching by Transformer achieves impressive performance for optical flow estimation. However, their…
MC-Stereo: Multi-peak Lookup and Cascade Search Range for Stereo Matching
Miaojie Feng, Junda Cheng, Hao Jia +4
Stereo matching is a fundamental task in scene comprehension. In recent years, the method based on iterative optimization has shown promise in stereo matching. However, the current…
Iterative Geometry Encoding Volume for Stereo Matching
Gangwei Xu, Xianqi Wang, Xiaohuan Ding +1
Recurrent All-Pairs Field Transforms (RAFT) has shown great potentials in matching tasks. However, all-pairs correlations lack non-local geometry knowledge and have difficulties ta…
CGI-Stereo: Accurate and Real-Time Stereo Matching via Context and Geometry Interaction
Gangwei Xu, Huan Zhou, Xin Yang
In this paper, we propose CGI-Stereo, a novel neural network architecture that can concurrently achieve real-time performance, competitive accuracy, and strong generalization abili…