2 papers
cs.CV2026
Rethinking Monocular Depth Embedding for Generalized Stereo Matching
Libo Lin, Shuangli Du, Minghua Zhao +3
Generally, monocular methods capture rich contextual priors but lack geometric precision, whereas stereo methods are geometrically accurate yet struggle in textureless and occluded…
cs.CV2025
Domain Generalized Stereo Matching with Uncertainty-guided Data Augmentation
Shuangli Du, Jing Wang, Minghua Zhao +2
State-of-the-art stereo matching (SM) models trained on synthetic data often fail to generalize to real data domains due to domain differences, such as color, illumination, contras…