Showing 2025Show all
3 papers · 1 filter
cs.CV2025
MAGIC: Learning from Visibility Asymmetry for Unsupervised Stereo Matching
Peng Xu, Zhiyu Xiang, Tingming Bai +5
Learning disparity in occluded regions remains difficult for unsupervised stereo matching. Photometric supervision lacks valid target-view correspondences in these regions, while t…
cs.CV2025
CVFusion: Cross-View Fusion of 4D Radar and Camera for 3D Object Detection
Hanzhi Zhong, Zhiyu Xiang, Ruoyu Xu +6
4D radar has received significant attention in autonomous driving thanks to its robustness under adverse weathers. Due to the sparse points and noisy measurements of the 4D radar,…
cs.CV2025
MIDAS: Modeling Ground-Truth Distributions with Dark Knowledge for Domain Generalized Stereo Matching
Peng Xu, Zhiyu Xiang, Jingyun Fu +3
Despite the significant advances in domain generalized stereo matching, existing methods still exhibit domain-specific preferences when transferring from synthetic to real domains,…