Body Meshes as Points

TL;DR

This paper introduces BMP, a single-stage method for multi-person 3D body mesh estimation that improves efficiency and accuracy by representing persons as points in space and directly predicting their meshes.

Contribution

BMP is the first single-stage model that concurrently localizes person points and estimates body meshes, reducing complexity and enhancing performance in multi-person scenes.

Findings

Achieves state-of-the-art efficiency on benchmarks.

Demonstrates high accuracy in complex scenes with occlusions.

Outperforms existing multi-stage methods in speed and precision.

Abstract

We consider the challenging multi-person 3D body mesh estimation task in this work. Existing methods are mostly two-stage based--one stage for person localization and the other stage for individual body mesh estimation, leading to redundant pipelines with high computation cost and degraded performance for complex scenes (e.g., occluded person instances). In this work, we present a single-stage model, Body Meshes as Points (BMP), to simplify the pipeline and lift both efficiency and performance. In particular, BMP adopts a new method that represents multiple person instances as points in the spatial-depth space where each point is associated with one body mesh. Hinging on such representations, BMP can directly predict body meshes for multiple persons in a single stage by concurrently localizing person instance points and estimating the corresponding body meshes. To better reason about depth ordering of all the persons within the same scene, BMP designs a simple yet effective inter-instance ordinal depth loss to obtain depth-coherent body mesh estimation. BMP also introduces a novel keypoint-aware augmentation to enhance model robustness to occluded person instances. Comprehensive experiments on benchmarks Panoptic, MuPoTS-3D and 3DPW clearly demonstrate the state-of-the-art efficiency of BMP for multi-person body mesh estimation, together with outstanding accuracy. Code can be found at: https://github.com/jfzhang95/BMP.