CVAILGNov 24, 2021

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

arXiv:2111.12707v4389 citationsHas Code
Originality Highly original
AI Analysis

This work solves the inverse problem of estimating 3D poses from 2D videos for computer vision applications, representing an incremental advance by introducing a novel method for a known bottleneck.

The paper tackles the problem of 3D human pose estimation from monocular videos by addressing depth ambiguity and self-occlusion through a multi-hypothesis approach, achieving state-of-the-art results with a 3% improvement on the Human3.6M dataset.

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}.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes