AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sun, Qingping, Wang, Yanjun, Zeng, Ailing, Yin, Wanqi, Wei, Chen, Wang, Wenjia, Mei, Haiyi, Leung, Chi Sing, Liu, Ziwei, Yang, Lei, Cai, Zhongang
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914729830645760
author Sun, Qingping
Wang, Yanjun
Zeng, Ailing
Yin, Wanqi
Wei, Chen
Wang, Wenjia
Mei, Haiyi
Leung, Chi Sing
Liu, Ziwei
Yang, Lei
Cai, Zhongang
author_facet Sun, Qingping
Wang, Yanjun
Zeng, Ailing
Yin, Wanqi
Wei, Chen
Wang, Wenjia
Mei, Haiyi
Leung, Chi Sing
Liu, Ziwei
Yang, Lei
Cai, Zhongang
contents Expressive human pose and shape estimation (a.k.a. 3D whole-body mesh recovery) involves the human body, hand, and expression estimation. Most existing methods have tackled this task in a two-stage manner, first detecting the human body part with an off-the-shelf detection model and inferring the different human body parts individually. Despite the impressive results achieved, these methods suffer from 1) loss of valuable contextual information via cropping, 2) introducing distractions, and 3) lacking inter-association among different persons and body parts, inevitably causing performance degradation, especially for crowded scenes. To address these issues, we introduce a novel all-in-one-stage framework, AiOS, for multiple expressive human pose and shape recovery without an additional human detection step. Specifically, our method is built upon DETR, which treats multi-person whole-body mesh recovery task as a progressive set prediction problem with various sequential detection. We devise the decoder tokens and extend them to our task. Specifically, we first employ a human token to probe a human location in the image and encode global features for each instance, which provides a coarse location for the later transformer block. Then, we introduce a joint-related token to probe the human joint in the image and encoder a fine-grained local feature, which collaborates with the global feature to regress the whole-body mesh. This straightforward but effective model outperforms previous state-of-the-art methods by a 9% reduction in NMVE on AGORA, a 30% reduction in PVE on EHF, a 10% reduction in PVE on ARCTIC, and a 3% reduction in PVE on EgoBody.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17934
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation
Sun, Qingping
Wang, Yanjun
Zeng, Ailing
Yin, Wanqi
Wei, Chen
Wang, Wenjia
Mei, Haiyi
Leung, Chi Sing
Liu, Ziwei
Yang, Lei
Cai, Zhongang
Computer Vision and Pattern Recognition
Expressive human pose and shape estimation (a.k.a. 3D whole-body mesh recovery) involves the human body, hand, and expression estimation. Most existing methods have tackled this task in a two-stage manner, first detecting the human body part with an off-the-shelf detection model and inferring the different human body parts individually. Despite the impressive results achieved, these methods suffer from 1) loss of valuable contextual information via cropping, 2) introducing distractions, and 3) lacking inter-association among different persons and body parts, inevitably causing performance degradation, especially for crowded scenes. To address these issues, we introduce a novel all-in-one-stage framework, AiOS, for multiple expressive human pose and shape recovery without an additional human detection step. Specifically, our method is built upon DETR, which treats multi-person whole-body mesh recovery task as a progressive set prediction problem with various sequential detection. We devise the decoder tokens and extend them to our task. Specifically, we first employ a human token to probe a human location in the image and encode global features for each instance, which provides a coarse location for the later transformer block. Then, we introduce a joint-related token to probe the human joint in the image and encoder a fine-grained local feature, which collaborates with the global feature to regress the whole-body mesh. This straightforward but effective model outperforms previous state-of-the-art methods by a 9% reduction in NMVE on AGORA, a 30% reduction in PVE on EHF, a 10% reduction in PVE on ARCTIC, and a 3% reduction in PVE on EgoBody.
title AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.17934