PulseAugur
LIVE 12:23:43
research · [2 sources] ·
0
research

ETCH-X and OmniFit advance 3D clothed human body fitting with new methods

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 2 sources

Researchers have developed ETCH-X, an advanced method for fitting parametric body models to 3D scans of clothed humans. This new approach improves upon its predecessor by incorporating a "tightness-aware" fitting paradigm to handle clothing dynamics and extending expressiveness with SMPL-X. ETCH-X utilizes implicit dense correspondences instead of explicit markers for greater robustness and fine-grained detail, achieving significant performance gains on various datasets. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Advances in 3D body fitting can improve downstream tasks like animation and texturing, potentially impacting virtual reality and digital content creation.

RANK_REASON The cluster contains two arXiv papers detailing new methods for 3D human body fitting.

Read on arXiv cs.CV →

COVERAGE [2]

  1. arXiv cs.CV TIER_1 · Xiaoben Li, Jingyi Wu, Zeyu Cai, Siyuan Yu, Boqian Li, Yuliang Xiu ·

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

    arXiv:2604.08548v3 Announce Type: replace 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 …

  2. arXiv cs.CV TIER_1 · Zhenyu Zhang ·

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

    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, espe…

RELATED ENTITIES

RELATED TOPICS