PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation

TL;DR

PandaNet is a novel single-shot, anchor-based deep learning model that efficiently estimates 3D poses for multiple people in images, including low-resolution scenarios, without post-processing.

Contribution

It introduces a unified approach combining detection and pose estimation, with strategies for overlapping people and scale-joint imbalance, advancing multi-person 3D pose estimation.

Findings

Outperforms previous methods on multiple datasets

Handles large numbers of people at low resolution

Does not require post-processing for joint regrouping

Abstract

Recently, several deep learning models have been proposed for 3D human pose estimation. Nevertheless, most of these approaches only focus on the single-person case or estimate 3D pose of a few people at high resolution. Furthermore, many applications such as autonomous driving or crowd analysis require pose estimation of a large number of people possibly at low-resolution. In this work, we present PandaNet (Pose estimAtioN and Dectection Anchor-based Network), a new single-shot, anchor-based and multi-person 3D pose estimation approach. The proposed model performs bounding box detection and, for each detected person, 2D and 3D pose regression into a single forward pass. It does not need any post-processing to regroup joints since the network predicts a full 3D pose for each bounding box and allows the pose estimation of a possibly large number of people at low resolution. To manage people overlapping, we introduce a Pose-Aware Anchor Selection strategy. Moreover, as imbalance exists between different people sizes in the image, and joints coordinates have different uncertainties depending on these sizes, we propose a method to automatically optimize weights associated to different people scales and joints for efficient training. PandaNet surpasses previous single-shot methods on several challenging datasets: a multi-person urban virtual but very realistic dataset (JTA Dataset), and two real world 3D multi-person datasets (CMU Panoptic and MuPoTS-3D).