AI Paper Atlas

Research map / 3D vision / Face and shape

Text to Layer-wise 3D Clothed Human Generation

Junting Dong, Qi Fang, Zehuan Huang, Xudong XU, Jingbo Wang, Sida Peng, Bo Dai

ECCV 2024 · 3D vision › Face and shape · approach: Clothed human modeling

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
model clothed human as layer-wise disentangled NeRFs instead of holistic single-stage modelTELA vs DreamWaltz · Text-to-3D clothed human generationFID: 142.6 -> 125.9Improved
use disentangled layer-wise modeling instead of holistic DreamWaltz in user studyTELA · User study overall qualitypreference (%): 71.46%Improved
add transparency-based stratified composition instead of max-density fusion of layers (ablation)TELA · Qualitative ablation (Figure 6)layer penetration (qualitative)Improved
add cloth-only SDS loss (dual SDS losses) (ablation)TELA · Qualitative ablation (Figure 7)cloth-body disentanglement (qualitative)Improved
add 2D skeleton-conditioned ControlNet SDS for cloth generation composed with the bodyTELA · Cloth generation vs DreamFusion/Magic3D/ProlificDreamermulti-face problem (qualitative)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy