Humans in 4D: Reconstructing and Tracking Humans with Transformers

We present an approach to reconstruct humans and track them over time. At the core of our approach, we propose a fully "transformerized" version of a network for human mesh recovery. This network, HMR 2.0, advances the state of the art and shows the capability to analyze unusual poses that have in the past been difficult to reconstruct from single images. To analyze video, we use 3D reconstructions from HMR 2.0 as input to a tracking system that operates in 3D. This enables us to deal with multiple people and maintain identities through occlusion events. Our complete approach, 4DHumans, achieves state-of-the-art results for tracking people from monocular video. Furthermore, we demonstrate the effectiveness of HMR 2.0 on the downstream task of action recognition, achieving significant improvements over previous pose-based action recognition approaches. Our code and models are available on the project website: https://shubham-goel.github.io/4dhumans/.

1. Introduction

In this paper, we present a fully transformer-based approach for recovering 3D meshes of human bodies from single images, and tracking them over time in video. We obtain unprecedented accuracy in our single-image 3D reconstructions (see Figure 1) even for unusual poses where previous approaches struggle. In video, we link these reconstructions over time by 3D tracking, in the process bridging gaps due to occlusion or detection failures. These 4D reconstructions can be seen on the project webpage.