DeepAI AI Chat
Log In Sign Up

Body Meshes as Points

by   Jianfeng Zhang, et al.
National University of Singapore
ByteDance Inc.

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:


Single-Stage Multi-Person Pose Machines

Multi-person pose estimation is a challenging problem. Existing methods ...

CenterHMR: a Bottom-up Single-shot Method for Multi-person 3D Mesh Recovery from a Single Image

In this paper, we propose a method to recover multi-person 3D mesh from ...

AdaptivePose++: A Powerful Single-Stage Network for Multi-Person Pose Regression

Multi-person pose estimation generally follows top-down and bottom-up pa...

MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose

Reconstructing multi-human body mesh from a single monocular image is an...

KAMA: 3D Keypoint Aware Body Mesh Articulation

We present KAMA, a 3D Keypoint Aware Mesh Articulation approach that all...

Occluded Human Mesh Recovery

Top-down methods for monocular human mesh recovery have two stages: (1) ...

Smooth Mesh Estimation from Depth Data using Non-Smooth Convex Optimization

Meshes are commonly used as 3D maps since they encode the topology of th...