English

Towards Balanced Multi-Modal Learning in 3D Human Pose Estimation

Computer Vision and Pattern Recognition 2026-03-17 v5 Artificial Intelligence

Abstract

3D human pose estimation (3D HPE) has emerged as a prominent research topic, particularly in the realm of RGB-based methods. However, the use of RGB images is often limited by issues such as occlusion and privacy constraints. Consequently, multi-modal sensing, which leverages non-intrusive sensors, is gaining increasing attention. Nevertheless, multi-modal 3D HPE still faces challenges, including modality imbalance. In this work, we introduce a novel balanced multi-modal learning method for 3D HPE, which harnesses the power of RGB, LiDAR, mmWave, and WiFi. Specifically, we propose a Shapley value-based contribution algorithm to assess the contribution of each modality and detect modality imbalance. To address this imbalance, we design a modality learning regulation strategy that decelerates the learning process during the early stages of training. We conduct extensive experiments on the widely adopted multi-modal dataset, MM-Fi, demonstrating the superiority of our approach in enhancing 3D pose estimation under complex conditions. Our source code is available at https://github.com/MICLAB-BUPT/AWC.

Keywords

Cite

@article{arxiv.2501.05264,
  title  = {Towards Balanced Multi-Modal Learning in 3D Human Pose Estimation},
  author = {Mengshi Qi and Jiaxuan Peng and Xianlin Zhang and Huadong Ma},
  journal= {arXiv preprint arXiv:2501.05264},
  year   = {2026}
}

Comments

Accepted by CVPR 2026

R2 v1 2026-06-28T21:01:18.645Z