DiffCorr: Conditional Diffusion Model with Reliable Pseudo-Label Guidance for Unsupervised Point Cloud Shape Correspondence
Jiacheng Deng, Jiahao Lu, Zhixin Cheng, Wenfei Yang
Abstract
Unsupervised point cloud shape correspondence aims to establish dense correspondences between source and target point clouds. Existing methods universally follow a one-step paradigm to obtain shape correspondence directly, but it often fails in large-scale motions of humans and animals. To address this challenge, we propose a conditional Diffusion model with reliable pseudo-label guidance for unsupervised point cloud shape Correspondence (DiffCorr), including a transformer-based conditional diffusion model and a reliable pseudo-label generator. The proposed DiffCorr enjoys several merits. Firstly, the transformer-based conditional diffusion model implements a coarse-to-fine optimization for coarse correspondences. Secondly, we design a reliable pseudo-label generator to provide high-quality pseudo-labels for training. Extensive experiments on four human and animal datasets demonstrate that DiffCorr surpasses state-of-the-art methods and exhibits favorable generalization capabilities.
BibTeX
@article{Deng_Lu_Cheng_Yang_2025, title={DiffCorr: Conditional Diffusion Model with Reliable Pseudo-Label Guidance for Unsupervised Point Cloud Shape Correspondence}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/32273}, DOI={10.1609/aaai.v39i3.32273}, abstractNote={Unsupervised point cloud shape correspondence aims to establish dense correspondences between source and target point clouds. Existing methods universally follow a one-step paradigm to obtain shape correspondence directly, but it often fails in large-scale motions of humans and animals. To address this challenge, we propose a conditional Diffusion model with reliable pseudo-label guidance for unsupervised point cloud shape Correspondence (DiffCorr), including a transformer-based conditional diffusion model and a reliable pseudo-label generator. The proposed DiffCorr enjoys several merits. Firstly, the transformer-based conditional diffusion model implements a coarse-to-fine optimization for coarse correspondences. Secondly, we design a reliable pseudo-label generator to provide high-quality pseudo-labels for training. Extensive experiments on four human and animal datasets demonstrate that DiffCorr surpasses state-of-the-art methods and exhibits favorable generalization capabilities.}, number={3}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Deng, Jiacheng and Lu, Jiahao and Cheng, Zhixin and Yang, Wenfei}, year={2025}, month={Apr.}, pages={2690-2698} }