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

NeurIPS 2023  ·  Zhongang Cai, Wanqi Yin, Ailing Zeng, Chen Wei, Qingping Sun, Yanjun Wang, Hui En Pang, Haiyi Mei, Mingyuan Zhang, Lei Zhang, Chen Change Loy, Lei Yang, Ziwei Liu ·

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/

PDF Abstract NeurIPS 2023 PDF NeurIPS 2023 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
3D Human Pose Estimation 3DPW SMPLer-X MPJPE 75.2 # 44
3D Multi-Person Mesh Recovery AGORA SMPLer-X FB-NMVE 107.2 # 1
B-NMVE 68.3 # 1
FB-MVE 99.7 # 1
F-MVE 29.9 # 1
LH/RH-MVE 39.3 # 1
3D Human Reconstruction EHF SMPLer-X MPVPE 62.4 # 2
PA V2V (mm), whole body 37.1 # 2
3D Human Pose Estimation UBody SMPLer-X PVE-All 57.5 # 2
PVE-Hands 40.2 # 2
PVE-Face 21.6 # 3
PA-PVE-All 31.9 # 2
PA-PVE-Hands 10.3 # 1
PA-PVE-Face 2.8 # 3

Methods


No methods listed for this paper. Add relevant methods here