English

PointCMC: Cross-Modal Multi-Scale Correspondences Learning for Point Cloud Understanding

Computer Vision and Pattern Recognition 2022-11-24 v2

Abstract

Some self-supervised cross-modal learning approaches have recently demonstrated the potential of image signals for enhancing point cloud representation. However, it remains a question on how to directly model cross-modal local and global correspondences in a self-supervised fashion. To solve it, we proposed PointCMC, a novel cross-modal method to model multi-scale correspondences across modalities for self-supervised point cloud representation learning. In particular, PointCMC is composed of: (1) a local-to-local (L2L) module that learns local correspondences through optimized cross-modal local geometric features, (2) a local-to-global (L2G) module that aims to learn the correspondences between local and global features across modalities via local-global discrimination, and (3) a global-to-global (G2G) module, which leverages auxiliary global contrastive loss between the point cloud and image to learn high-level semantic correspondences. Extensive experiment results show that our approach outperforms existing state-of-the-art methods in various downstream tasks such as 3D object classification and segmentation. Code will be made publicly available upon acceptance.

Keywords

Cite

@article{arxiv.2211.12032,
  title  = {PointCMC: Cross-Modal Multi-Scale Correspondences Learning for Point Cloud Understanding},
  author = {Honggu Zhou and Xiaogang Peng and Jiawei Mao and Zizhao Wu and Ming Zeng},
  journal= {arXiv preprint arXiv:2211.12032},
  year   = {2022}
}

Comments

In order to revise the paper

R2 v1 2026-06-28T06:33:47.819Z