English

Diff-Reg v1: Diffusion Matching Model for Registration Problem

Computer Vision and Pattern Recognition 2024-07-26 v4

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 construction. Our approach treats correspondence estimation as a denoising diffusion process within the doubly stochastic matrix space, which gradually denoises (refines) a doubly stochastic matching matrix to the ground-truth one for high-quality correspondence estimation. It involves a forward diffusion process that gradually introduces Gaussian noise into the ground truth matching matrix and a reverse denoising process that iteratively refines the noisy matching matrix. In particular, the feature extraction from the backbone occurs only once during the inference phase. Our lightweight denoising module utilizes the same feature at each reverse sampling step. Evaluation of our method on both 3D and 2D3D registration tasks confirms its effectiveness. The code is available at https://github.com/wuqianliang/Diff-Reg.

Keywords

Cite

@article{arxiv.2403.19919,
  title  = {Diff-Reg v1: Diffusion Matching Model for Registration Problem},
  author = {Qianliang Wu and Haobo Jiang and Lei Luo and Jun Li and Yaqing Ding and Jin Xie and Jian Yang},
  journal= {arXiv preprint arXiv:2403.19919},
  year   = {2024}
}

Comments

arXiv admin note: text overlap with arXiv:2401.00436

R2 v1 2026-06-28T15:37:54.416Z