Diff-Reg v1: Diffusion Matching Model for Registration Problem

arXiv:2403.19919v1 Announce Type: new
Abstract: Establishing reliable correspondences is essential for registration tasks such as 3D and 2D3D registration. Existing methods commonly leverage geometric or semantic point features to generate potential correspondences. However, these features may face challenges such as large deformation, scale inconsistency, and ambiguous matching problems (e.g., symmetry). Additionally, many previous methods, which rely on single-pass prediction, may struggle with local minima in complex scenarios. To mitigate these challenges, we introduce a diffusion matching model for robust correspondence …

abstract arxiv challenges cs.cv diff diffusion face features generate however registration scale semantic symmetry tasks type