ETCH-X: Robustify Expressive Body Fitting to Clothed Humans with Composable Datasets
2026-04-09 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors improved a method called ETCH to create ETCH-X, which fits 3D human body models more accurately to scans of clothed people. Their approach separates the process into two parts: one that removes clothing effects and another that matches detailed points on the body, helping it work better with clothes, poses, and partial data. They used different data sources to train these parts, enabling the system to handle complex body movements and hand details. Their method performs better than the original ETCH on both familiar and new datasets.
Human body fittingSMPL-X3D point cloudsClothing dynamicsDense correspondencesParametric body modelsPose variationAMASS datasetCLOTH3DMPJPE (Mean Per Joint Position Error)
Authors
Xiaoben Li, Jingyi Wu, Zeyu Cai, Siyuan Yu, Boqian Li, Yuliang Xiu
Abstract
Human body fitting, which aligns parametric body models such as SMPL to raw 3D point clouds of clothed humans, serves as a crucial first step for downstream tasks like animation and texturing. An effective fitting method should be both locally expressive-capturing fine details such as hands and facial features-and globally robust to handle real-world challenges, including clothing dynamics, pose variations, and noisy or partial inputs. Existing approaches typically excel in only one aspect, lacking an all-in-one solution. We upgrade ETCH to ETCH-X, which leverages a tightness-aware fitting paradigm to filter out clothing dynamics ("undress"), extends expressiveness with SMPL-X, and replaces explicit sparse markers (which are highly sensitive to partial data) with implicit dense correspondences ("dense fit") for more robust and fine-grained body fitting. Our disentangled "undress" and "dense fit" modular stages enable separate and scalable training on composable data sources, including diverse simulated garments (CLOTH3D), large-scale full-body motions (AMASS), and fine-grained hand gestures (InterHand2.6M), improving outfit generalization and pose robustness of both bodies and hands. Our approach achieves robust and expressive fitting across diverse clothing, poses, and levels of input completeness, delivering a substantial performance improvement over ETCH on both: 1) seen data, such as 4D-Dress (MPJPE-All, 33.0% ) and CAPE (V2V-Hands, 35.8% ), and 2) unseen data, such as BEDLAM2.0 (MPJPE-All, 80.8% ; V2V-All, 80.5% ). Code and models will be released at https://xiaobenli00.github.io/ETCH-X/.