VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild

by   Yifu Zhang, et al.

We present VoxelTrack for multi-person 3D pose estimation and tracking from a few cameras which are separated by wide baselines. It employs a multi-branch network to jointly estimate 3D poses and re-identification (Re-ID) features for all people in the environment. In contrast to previous efforts which require to establish cross-view correspondence based on noisy 2D pose estimates, it directly estimates and tracks 3D poses from a 3D voxel-based representation constructed from multi-view images. We first discretize the 3D space by regular voxels and compute a feature vector for each voxel by averaging the body joint heatmaps that are inversely projected from all views. We estimate 3D poses from the voxel representation by predicting whether each voxel contains a particular body joint. Similarly, a Re-ID feature is computed for each voxel which is used to track the estimated 3D poses over time. The main advantage of the approach is that it avoids making any hard decisions based on individual images. The approach can robustly estimate and track 3D poses even when people are severely occluded in some cameras. It outperforms the state-of-the-art methods by a large margin on three public datasets including Shelf, Campus and CMU Panoptic.


page 1

page 5

page 6

page 7

page 9

page 12

page 14


End-to-End Estimation of Multi-Person 3D Poses from Multiple Cameras

We present an approach to estimate 3D poses of multiple people from mult...

Multi-person 3D pose estimation from unlabelled data

Its numerous applications make multi-human 3D pose estimation a remarkab...

Shape-aware Multi-Person Pose Estimation from Multi-View Images

In this paper we contribute a simple yet effective approach for estimati...

Scene-aware Egocentric 3D Human Pose Estimation

Egocentric 3D human pose estimation with a single head-mounted fisheye c...

Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking

This paper introduces an approach for multi-human 3D pose estimation and...

Iterative Greedy Matching for 3D Human Pose Tracking from Multiple Views

In this work we propose an approach for estimating 3D human poses of mul...

Transformer-based Global 3D Hand Pose Estimation in Two Hands Manipulating Objects Scenarios

This report describes our 1st place solution to ECCV 2022 challenge on H...

Please sign up or login with your details

Forgot password? Click here to reset