ETCH-X: Robustify Expressive Body Fitting to Clothed Humans with Composable Datasets

Xiaoben Li; Jingyi Wu; Zeyu Cai; Siyuan Yu; Boqian Li; Yuliang Xiu

cs.CVApr 9, 2026

ETCH-X: Robustify Expressive Body Fitting to Clothed Humans with Composable Datasets

Authors: Xiaoben Li, Jingyi Wu, Zeyu Cai, Siyuan Yu, Boqian Li, Yuliang Xiu

Organizations: Zhejiang University · Westlake University · Shanghai Innovation Institute · Fudan University ·

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/.

Figures & tables

Figure 1: Strengths of ETCH-X . While NICP [ 31 ] , which uses implicit dense correspondence but lacks tightness-aware undressing, consistently produces overweight bodies from clothed scans ( A ), ETCH [ 24 ] , with tightness-aware undressing but sparse markers, fails to capture detailed body parts such as hands and face ( B ), and struggles with partial inputs due to missing markers ( C ). In contrast, our ETCH-X combines the strengths of both approaches, achieving robust and expressive fitting across diverse clothing, poses, and levels of input completeness ( D ).

Figure 2: Two stages of ETCH-X : (A) Masked Undress, (B) Dense Fit . In the Masked Undress stage, we take a clothed scan as input and compute the undressed body ( $\hat{\mathbf{y}}_{i}=\mathbf{x}_{i}+\hat{l}_{i}\hat{\mathbf{v}}_{i}$ ). In the Dense Fit stage, we implicitly learns the deforming field, which deforms the canonical SMPL-X into a posed one. Thanks to the decoupled design, the robustness to dynamic clothing and pose variations could be improved with simulated garments, i.e . , CLOTH3D [ 3 ] , and pose libraries, i.e . , AMASS [ 30 ] for body poses and InterHand2.6M [ 32 ] for hand poses, respectively.

Figure 3: Hand Refinement by Re-sampling. After obtaining initial body fitting, we re-sample points around the hand and fit hand model separately.

Groups	Methods	CAPE									4D-Dress
		CD $\downarrow$	V2V $\downarrow$				MPJPE $\downarrow$				CD $\downarrow$	V2V $\downarrow$				MPJPE $\downarrow$
		All	All	Hands	Head	Other	All	Hands	Head	Other	All	All	Hands	Head	Other	All	Hands	Head	Other
A.	NICP	-	1.736	2.741	1.184	1.827	2.074	2.565	1.042	1.597	-	4.085	6.224	3.323	3.993	4.862	6.142	2.540	3.521
A.	ArtEq	-	2.202	3.417	2.011	1.943	2.405	3.055	1.693	1.589	-	3.072	4.537	3.145	2.636	3.378	4.170	2.335	2.156
B.	IPNet	1.077	5.529	7.454	5.485	5.001	5.611	6.600	4.527	4.399	1.187	7.495	8.881	7.378	7.178	7.380	8.606	5.973	5.894
	PTF	1.194	2.341	3.880	2.038	2.099	2.641	3.377	1.720	1.767	1.207	3.297	4.938	3.338	2.785	3.567	4.607	2.612	2.248

Table 1: In-distribution Quantitative Comparison with SOTAs. ETCH-X clearly outperforms SOTAs, whether tightness-agnostic (A.) or -aware (B.), in both CAPE and 4D-Dress across almost all metrics. In 4D-Dress-V2V, it surpasses the ETCH by nearly

21.2\%

Table 5

Figure 4: Failure Case of ETCH [ 24 ] on BEDLAM2.0 . Two respresentative reasons for ETCH failure are incorrect part labeling (above) and inaccurate inner points (both). The failure is reflected in the large V2V (12.209cm) and MPJPE (15.031cm) errors of ETCH reported in Tab. 3

Table 7

Figure 5: Partial Augmentation . ETCH-X predicts better body poses with partial augmentation.

Figure 6: Scaling Analysis of ETCH-X . Increasing the amount of training data from CLOTH3D [ 3 ] (left) and AMASS [ 30 ] (right) does not necessarily improve performance: tightness accuracy saturates, while pose robustness continues to increase.

Settings	Hand LVD	Hand Classifier	Hand Data Augmentation	CAPE				4D-Dress
				V2V $\downarrow$		MPJPE $\downarrow$		V2V $\downarrow$		MPJPE $\downarrow$
				All	Hands	All	Hands	All	Hands	All	Hands
A.	✗	✗	✗	1.550	2.607	1.948	2.467	1.991	3.417	2.492	3.367
B.	✓	✗	✗	1.514	2.417	1.835	2.277	1.963	3.321	2.444	3.293
C.	✓	✓	✗	1.493	2.278	1.794	2.203	1.928	3.167	2.376	3.125
ETCH-X	✓	✓	✓	1.484	2.215	1.764	2.148	1.897	3.101	2.317	3.065

Table 6: Ablation Results of Hand Refinements.

Figure 7: Hand Refinement Results. ETCH-X produce much better hand poses with hand refinement.

Figure 8: Comparison with SOTAs on 4D-Dress.

Human Mesh Recovery

Human mesh recovery estimates articulated 3D body shape and pose from images, video, or other sensors for animation, tracking, and physical analysis.

See all 52 papers

OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Prediction
Apr 23, 2026Zeyu Cai, Yuliang Xiu, Renke Wang +83D Reconstruction Human Mesh Recovery
Nanjing University · Westlake University · Nanjing University of Science and Technology +2
Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need
Sep 10, 2026Margaret Kostyrko, Yuxuan Xue, Garvita Tiwari +1Non-Rigid Shape Correspondence 3D Human Reconstruction
University of Tübingen · Tübingen AI Center · Max Planck Institute for Informatics
SOMA: Unifying Parametric Human Body Models
Mar 17, 2026Jun Saito, Jiefeng Li, Michael de Ruyter +123D Morphable Models 3D Reconstruction
NVIDIA

Apr 23, 2026J/K move · Enter open · S save

OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Prediction

Zeyu Cai, Yuliang Xiu, Renke Wang, Zhijing Shao+7

Nanjing University · Westlake University · Nanjing University of Science and Technology+2

3D Reconstruction Human Mesh Recovery 3D Human Reconstruction

Open paper AskPDF arXiv

Fitting an underlying body model to 3D clothed human assets has been extensively studied, yet most approaches focus on either single-modal inputs such as point clouds or multi-view images alone, often requiring a known metric scale. This constraint is frequently impractical, especially for AI-generated assets where scale distortion is common. We propose OmniFit, a method that can seamlessly handle diverse multi-modal inputs, including full scans, partial depth observations, and image captures, while remaining scale-agnostic for both real and synthetic assets. Our key innovation is a simple yet effective conditional transformer decoder that directly maps surface points to dense body landmarks, which are then used for SMPL-X parameter fitting. In addition, an optional plug-and-play image adapter incorporates visual cues to compensate for missing geometric information. We further introduce a dedicated scale predictor that rescales subjects to canonical body proportions. OmniFit substantially outperforms state-of-the-art methods by 57.1 to 80.9 percent across daily and loose clothing scenarios. To the best of our knowledge, it is the first body fitting method to surpass multi-view optimization baselines and the first to achieve millimeter-level accuracy on the CAPE and 4D-DRESS benchmarks.

Abstract

Human Mesh Recovery

Explore similar work

OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Prediction

Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need

SOMA: Unifying Parametric Human Body Models