DiffCorr: Conditional Diffusion Model with Reliable Pseudo-Label Guidance for Unsupervised Point Cloud Shape Correspondence
Open Access
- 11 April 2025
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (3) , 2690-2698
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.Keywords
This publication has 9 references indexed in Scilit:
- Pamba: Enhancing Global Interaction in Point Clouds via State Space ModelProceedings of the AAAI Conference on Artificial Intelligence, 2025
- DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation2024
- Hierarchical Shape-Consistent Transformer for Unsupervised Point Cloud Shape CorrespondenceIEEE Transactions on Image Processing, 2023
- Non-Rigid Shape Registration via Deep Functional Maps Prior2023
- PVT v2: Improved baselines with pyramid vision transformerComputational Visual Media, 2022
- Point Transformer V2: Grouped Vector Attention and Partition-Based Pooling2022
- PCT: Point cloud transformerComputational Visual Media, 2021
- Dynamic Graph CNN for Learning on Point CloudsACM Transactions on Graphics, 2019
- Numerical Geometry of Non-Rigid Shapes2009