MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

Abstract

Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spatial and temporal relationships. However, those works ignore the fact that it is an inverse problem where multiple feasible solutions (i.e., hypotheses) exist. To relieve this limitation, we propose a Multi-Hypothesis Transformer (MHFormer) that learns spatio-temporal representations of multiple plausible pose hypotheses. In order to effectively model multi-hypothesis dependencies and build strong relationships across hypothesis features, the task is decomposed into three stages: (i) Generate multiple initial hypothesis representations; (ii) Model self-hypothesis communication, merge multiple hypotheses into a single converged representation and then partition it into several diverged hypotheses; (iii) Learn cross-hypothesis communication and aggregate the multi-hypothesis features to synthesize the final 3D pose. Through the above processes, the final representation is enhanced and the synthesized pose is much more accurate. Extensive experiments show that MHFormer achieves state-of-the-art results on two challenging datasets: Human3.6M and MPI-INF-3DHP. Without bells and whistles, its performance surpasses the previous best result by a large margin of 3% on Human3.6M. Code and models are available at \url{https://github.com/Vegetebird/MHFormer}.

Accepted by CVPR 2022. Open Sourced

References in corpus (9)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
• CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
• TransReID: Transformer-based Object Re-Identification
• A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification
• Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation
• Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction
• 3D Human Pose Estimation with Spatial and Temporal Transformers
• Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation