2 papers
cs.CV2026
TeaMatch: Teachable Cross-Modal Representation Learning for 2D-3D Matching
Chongjian Wang, Junjie Gao
Learning reliable correspondences between images and point clouds is fundamental for 2D-3D matching. Despite recent progress in detection-free methods, existing approaches primaril…
cs.CV2026
SHReg: Strictly Rotation-Equivariant Point Cloud Registration via Spherical Harmonics
Chongjian Wang, Junjie Gao
Point cloud registration critically depends on local features that are both distinctive and robust to arbitrary 3D rotations. Existing learning-based methods typically approximate…