SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, Zhongang, Yin, Wanqi, Zeng, Ailing, Wei, Chen, Sun, Qingping, Wang, Yanjun, Pang, Hui En, Mei, Haiyi, Zhang, Mingyuan, Zhang, Lei, Loy, Chen Change, Yang, Lei, Liu, Ziwei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913449536126976
author Cai, Zhongang
Yin, Wanqi
Zeng, Ailing
Wei, Chen
Sun, Qingping
Wang, Yanjun
Pang, Hui En
Mei, Haiyi
Zhang, Mingyuan
Zhang, Lei
Loy, Chen Change
Yang, Lei
Liu, Ziwei
author_facet Cai, Zhongang
Yin, Wanqi
Zeng, Ailing
Wei, Chen
Sun, Qingping
Wang, Yanjun
Pang, Hui En
Mei, Haiyi
Zhang, Mingyuan
Zhang, Lei
Loy, Chen Change
Yang, Lei
Liu, Ziwei
contents Expressive human pose and shape estimation (EHPS) unifies body, hands, and face motion capture with numerous applications. Despite encouraging progress, current state-of-the-art methods still depend largely on a confined set of training datasets. In this work, we investigate scaling up EHPS towards the first generalist foundation model (dubbed SMPLer-X), with up to ViT-Huge as the backbone and training with up to 4.5M instances from diverse data sources. With big data and the large model, SMPLer-X exhibits strong performance across diverse test benchmarks and excellent transferability to even unseen environments. 1) For the data scaling, we perform a systematic investigation on 32 EHPS datasets, including a wide range of scenarios that a model trained on any single dataset cannot handle. More importantly, capitalizing on insights obtained from the extensive benchmarking process, we optimize our training scheme and select datasets that lead to a significant leap in EHPS capabilities. 2) For the model scaling, we take advantage of vision transformers to study the scaling law of model sizes in EHPS. Moreover, our finetuning strategy turn SMPLer-X into specialist models, allowing them to achieve further performance boosts. Notably, our foundation model SMPLer-X consistently delivers state-of-the-art results on seven benchmarks such as AGORA (107.2 mm NMVE), UBody (57.4 mm PVE), EgoBody (63.6 mm PVE), and EHF (62.3 mm PVE without finetuning). Homepage: https://caizhongang.github.io/projects/SMPLer-X/
format Preprint
id arxiv_https___arxiv_org_abs_2309_17448
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation
Cai, Zhongang
Yin, Wanqi
Zeng, Ailing
Wei, Chen
Sun, Qingping
Wang, Yanjun
Pang, Hui En
Mei, Haiyi
Zhang, Mingyuan
Zhang, Lei
Loy, Chen Change
Yang, Lei
Liu, Ziwei
Computer Vision and Pattern Recognition
Expressive human pose and shape estimation (EHPS) unifies body, hands, and face motion capture with numerous applications. Despite encouraging progress, current state-of-the-art methods still depend largely on a confined set of training datasets. In this work, we investigate scaling up EHPS towards the first generalist foundation model (dubbed SMPLer-X), with up to ViT-Huge as the backbone and training with up to 4.5M instances from diverse data sources. With big data and the large model, SMPLer-X exhibits strong performance across diverse test benchmarks and excellent transferability to even unseen environments. 1) For the data scaling, we perform a systematic investigation on 32 EHPS datasets, including a wide range of scenarios that a model trained on any single dataset cannot handle. More importantly, capitalizing on insights obtained from the extensive benchmarking process, we optimize our training scheme and select datasets that lead to a significant leap in EHPS capabilities. 2) For the model scaling, we take advantage of vision transformers to study the scaling law of model sizes in EHPS. Moreover, our finetuning strategy turn SMPLer-X into specialist models, allowing them to achieve further performance boosts. Notably, our foundation model SMPLer-X consistently delivers state-of-the-art results on seven benchmarks such as AGORA (107.2 mm NMVE), UBody (57.4 mm PVE), EgoBody (63.6 mm PVE), and EHF (62.3 mm PVE without finetuning). Homepage: https://caizhongang.github.io/projects/SMPLer-X/
title SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.17448