ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

TL;DR

ATLAS is a high-fidelity human body model that explicitly separates shape and skeleton parameters, enabling more accurate pose fitting, detailed shape customization, and improved expressivity over existing models.

Contribution

The paper introduces ATLAS, a novel human body model that decouples shape and skeleton bases, learned from extensive high-resolution scans, improving pose fitting and shape expressivity.

Findings

Outperforms existing models in fitting unseen subjects in diverse poses.

Non-linear pose correctives better capture complex poses.

Enables independent control over body height and bone lengths.

Abstract

Parametric body models offer expressive 3D representation of humans across a wide range of poses, shapes, and facial expressions, typically derived by learning a basis over registered 3D meshes. However, existing human mesh modeling approaches struggle to capture detailed variations across diverse body poses and shapes, largely due to limited training data diversity and restrictive modeling assumptions. Moreover, the common paradigm first optimizes the external body surface using a linear basis, then regresses internal skeletal joints from surface vertices. This approach introduces problematic dependencies between internal skeleton and outer soft tissue, limiting direct control over body height and bone lengths. To address these issues, we present ATLAS, a high-fidelity body model learned from 600k high-resolution scans captured using 240 synchronized cameras. Unlike previous methods, we explicitly decouple the shape and skeleton bases by grounding our mesh representation in the human skeleton. This decoupling enables enhanced shape expressivity, fine-grained customization of body attributes, and keypoint fitting independent of external soft-tissue characteristics. ATLAS outperforms existing methods by fitting unseen subjects in diverse poses more accurately, and quantitative evaluations show that our non-linear pose correctives more effectively capture complex poses compared to linear models.