11 citations · 13 across the 2 of their papers we have counts for
5 papers
CLIP-FLow: Contrastive Learning by semi-supervised Iterative Pseudo labeling for Optical Flow Estimation
Zhiqi Zhang, Nitin Bansal, Changjiang Cai +4
Synthetic datasets are often used to pretrain end-to-end optical flow networks, due to the lack of a large amount of labeled, real-scene data. But major drops in accuracy occur whe…
Do End-to-end Stereo Algorithms Under-utilize Information?
Changjiang Cai, Philippos Mordohai
Deep networks for stereo matching typically leverage 2D or 3D convolutional encoder-decoder architectures to aggregate cost and regularize the cost volume for accurate disparity es…
Matching-space Stereo Networks for Cross-domain Generalization
Changjiang Cai, Matteo Poggi, Stefano Mattoccia +1
End-to-end deep networks represent the state of the art for stereo matching. While excelling on images framing environments similar to the training set, major drops in accuracy occ…
Towards Robust RGB-D Human Mesh Recovery
Ren Li, Changjiang Cai, Georgios Georgakis +3
We consider the problem of human pose estimation. While much recent work has focused on the RGB domain, these techniques are inherently under-constrained since there can be many 3D…
CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation
Konstantinos Batsos, Changjiang Cai, Philippos Mordohai
Recently, there has been a paradigm shift in stereo matching with learning-based methods achieving the best results on all popular benchmarks. The success of these methods is due t…