4 papers
SGMatch: Semantic-Guided Non-Rigid Shape Matching with Flow Regularization
Tianwei Ye, Xiaoguang Mei, Yifan Xia +3
Establishing accurate point-to-point correspondences between non-rigid 3D shapes remains a critical challenge, particularly under non-isometric deformations and topological noise.…
DcMatch: Unsupervised Multi-Shape Matching with Dual-Level Consistency
Tianwei Ye, Yong Ma, Xiaoguang Mei
Establishing point-to-point correspondences across multiple 3D shapes is a fundamental problem in computer vision and graphics. In this paper, we introduce DcMatch, a novel unsuper…
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…
SpecDM: Hyperspectral Dataset Synthesis with Pixel-level Semantic Annotations
Wendi Liu, Pei Yang, Wenhui Hong +2
In hyperspectral remote sensing field, some downstream dense prediction tasks, such as semantic segmentation (SS) and change detection (CD), rely on supervised learning to improve…