Multi-person 3D pose estimation from unlabelled data

TL;DR

This paper introduces a self-supervised deep learning approach using Graph Neural Networks and MLPs for multi-person 3D pose estimation from multiple RGB views, effectively handling identification, occlusion, and noise without requiring labeled 3D data.

Contribution

It proposes a novel self-supervised framework combining GNNs and MLPs for multi-view 3D pose estimation, eliminating the need for large annotated datasets.

Findings

Effective cross-view person correspondence prediction

Robust 3D pose estimation despite occlusions and noise

Avoids reliance on large labeled 3D datasets

Abstract

Its numerous applications make multi-human 3D pose estimation a remarkably impactful area of research. Nevertheless, assuming a multiple-view system composed of several regular RGB cameras, 3D multi-pose estimation presents several challenges. First of all, each person must be uniquely identified in the different views to separate the 2D information provided by the cameras. Secondly, the 3D pose estimation process from the multi-view 2D information of each person must be robust against noise and potential occlusions in the scenario. In this work, we address these two challenges with the help of deep learning. Specifically, we present a model based on Graph Neural Networks capable of predicting the cross-view correspondence of the people in the scenario along with a Multilayer Perceptron that takes the 2D points to yield the 3D poses of each person. These two models are trained in a self-supervised manner, thus avoiding the need for large datasets with 3D annotations.