arXiv:2508.15767cs.CV2025-08ICCV被引 13

ATLAS通过解耦骨骼与形体参数,实现更精准的人体建模。

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

  • 基于人体骨架解耦形体与骨骼基底,提升建模精度
  • 在60万张高分辨率扫描数据上训练,支持复杂姿态还原
  • 适合需要精细人体控制的动画与虚拟人应用

参数化人体模型能表达多样姿态、体型和面部表情,通常通过学习注册3D网格的基底得到。然而,现有方法受限于训练数据多样性不足及建模假设僵化,难以捕捉不同姿态与体型的细节差异。传统方法先用线性基底优化外部表面,再从表面顶点回归内部关节,导致骨骼与软组织间存在不良依赖,难以直接控制身高与骨长。为此,我们提出ATLAS,基于240台同步相机采集的60万张高分辨率扫描数据训练。不同于以往方法,我们以人体骨架为基准,显式解耦形状与骨骼基底。该设计增强了形状表现力,支持对身体属性的细粒度定制,并实现与外部软组织无关的关键点拟合。定量评估显示,相较于线性模型,非线性姿态校正项更有效捕捉复杂姿态,且在未见受试者多样姿态下的拟合精度显著优于现有方法。

原文摘要 · Abstract (English)

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.

人体建模参数化模型姿态估计

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。