Saved in:
Bibliographic Details
Main Authors: Wang, Kaiwen, Zheng, Kaili, Shi, Yiming, Guo, Chenyi, Wu, Ji
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.13282
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915628071256064
author Wang, Kaiwen
Zheng, Kaili
Shi, Yiming
Guo, Chenyi
Wu, Ji
author_facet Wang, Kaiwen
Zheng, Kaili
Shi, Yiming
Guo, Chenyi
Wu, Ji
contents Multi-person human mesh recovery from a single image is a challenging task, hindered by the scarcity of in-the-wild training data. Prevailing in-the-wild human mesh pseudo-ground-truth (pGT) generation pipelines are single-person-centric, where each human is processed individually without joint optimization. This oversight leads to a lack of scene-level consistency, producing individuals with conflicting depths and scales within the same image. To address this, we introduce Depth-conditioned Translation Optimization (DTO), a novel optimization-based method that jointly refines the camera-space translations of all individuals in a crowd. By leveraging anthropometric priors on human height and depth cues from a monocular depth estimator, DTO solves for a scene-consistent placement of all subjects within a principled Maximum a posteriori (MAP) framework. Applying DTO to the 4D-Humans dataset, we construct DTO-Humans, a new large-scale pGT dataset of 0.56M high-quality, scene-consistent multi-person images, featuring dense crowds with an average of 4.8 persons per image. Furthermore, we propose Metric-Aware HMR, an end-to-end network that directly estimates human mesh and camera parameters in metric scale. This is enabled by a camera branch and a relative metric loss that enforces plausible relative scales. Extensive experiments demonstrate that our method achieves state-of-the-art performance on relative depth reasoning and human mesh recovery. Code is available at: https://github.com/gouba2333/MA-HMR.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13282
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space
Wang, Kaiwen
Zheng, Kaili
Shi, Yiming
Guo, Chenyi
Wu, Ji
Computer Vision and Pattern Recognition
Multi-person human mesh recovery from a single image is a challenging task, hindered by the scarcity of in-the-wild training data. Prevailing in-the-wild human mesh pseudo-ground-truth (pGT) generation pipelines are single-person-centric, where each human is processed individually without joint optimization. This oversight leads to a lack of scene-level consistency, producing individuals with conflicting depths and scales within the same image. To address this, we introduce Depth-conditioned Translation Optimization (DTO), a novel optimization-based method that jointly refines the camera-space translations of all individuals in a crowd. By leveraging anthropometric priors on human height and depth cues from a monocular depth estimator, DTO solves for a scene-consistent placement of all subjects within a principled Maximum a posteriori (MAP) framework. Applying DTO to the 4D-Humans dataset, we construct DTO-Humans, a new large-scale pGT dataset of 0.56M high-quality, scene-consistent multi-person images, featuring dense crowds with an average of 4.8 persons per image. Furthermore, we propose Metric-Aware HMR, an end-to-end network that directly estimates human mesh and camera parameters in metric scale. This is enabled by a camera branch and a relative metric loss that enforces plausible relative scales. Extensive experiments demonstrate that our method achieves state-of-the-art performance on relative depth reasoning and human mesh recovery. Code is available at: https://github.com/gouba2333/MA-HMR.
title Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.13282