Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation

TL;DR

This paper introduces a weakly-supervised, geometry-aware 3D human pose representation learned from multi-view data and 2D keypoints, improving 3D pose estimation robustness and generalizability across environments.

Contribution

It proposes a novel skeleton-based auto-encoder with view synthesis and representation consistency constraints for learning 3D geometry-aware pose representations using minimal supervision.

Findings

Significantly improves state-of-the-art 3D pose estimation accuracy.

Effective in cross-environment generalization.

Utilizes only 2D keypoints and multi-view data for training.

Abstract

Recent studies have shown remarkable advances in 3D human pose estimation from monocular images, with the help of large-scale in-door 3D datasets and sophisticated network architectures. However, the generalizability to different environments remains an elusive goal. In this work, we propose a geometry-aware 3D representation for the human pose to address this limitation by using multiple views in a simple auto-encoder model at the training stage and only 2D keypoint information as supervision. A view synthesis framework is proposed to learn the shared 3D representation between viewpoints with synthesizing the human pose from one viewpoint to the other one. Instead of performing a direct transfer in the raw image-level, we propose a skeleton-based encoder-decoder mechanism to distil only pose-related representation in the latent space. A learning-based representation consistency constraint is further introduced to facilitate the robustness of latent 3D representation. Since the learnt representation encodes 3D geometry information, mapping it to 3D pose will be much easier than conventional frameworks that use an image or 2D coordinates as the input of 3D pose estimator. We demonstrate our approach on the task of 3D human pose estimation. Comprehensive experiments on three popular benchmarks show that our model can significantly improve the performance of state-of-the-art methods with simply injecting the representation as a robust 3D prior.