4 papers
Make Geometry Matter for Spatial Reasoning
Shihua Zhang, Qiuhong Shen, Shizun Wang +2
Empowered by large-scale training, vision-language models (VLMs) achieve strong image and video understanding, yet their ability to perform spatial reasoning in both static scenes…
Deep Learning Reforms Image Matching: A Survey and Outlook
Shihua Zhang, Zizhuo Li, Kaining Zhang +5
Image matching, which establishes correspondences between two-view images to recover 3D structure and camera geometry, serves as a cornerstone in computer vision and underpins a wi…
CoMatch: Dynamic Covisibility-Aware Transformer for Bilateral Subpixel-Level Semi-Dense Image Matching
Zizhuo Li, Yifan Lu, Linfeng Tang +2
This prospective study proposes CoMatch, a novel semi-dense image matcher with dynamic covisibility awareness and bilateral subpixel accuracy. Firstly, observing that modeling cont…
Selecting and Pruning: A Differentiable Causal Sequentialized State-Space Model for Two-View Correspondence Learning
Xiang Fang, Shihua Zhang, Hao Zhang +3
Two-view correspondence learning aims to discern true and false correspondences between image pairs by recognizing their underlying different information. Previous methods either t…