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

TL;DR

SMPLer-X is a large-scale foundation model for expressive human pose and shape estimation, trained on diverse datasets with a ViT-Huge backbone, achieving state-of-the-art results and strong transferability across multiple benchmarks.

Contribution

This work introduces SMPLer-X, the first generalist foundation model for EHPS, leveraging extensive data scaling and vision transformer architectures to improve performance and transferability.

Findings

SMPLer-X achieves state-of-the-art results on seven benchmarks.

Data and model scaling significantly enhance EHPS capabilities.

Finetuning further boosts model performance.

Abstract

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/