AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Dynamic Texture Modeling of 3D Clothed Gaussian Avatars from a Single Video

Seungeun Lee, SeungJun Moon, Hah Min Lew, Ji-Su Kang, Gyeong-Moon Park

ICLR 2026 · 3D vision › Gaussian splatting · approach: Animatable Gaussian human avatars

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
add physics-inspired finite-difference dynamics with regularization (ablation)GNN deformer · 4D-DressPSNR: 25.21 -> 26.05Improved
add adaptive spring stiffness (ablation)GNN deformer · 4D-DressPSNR: 26.05 -> 26.44Improved
add edge-feature message passing (ablation)GNN deformer · 4D-DressPSNR: 26.44 -> 27.12Improved
add velocity encoding with window 11 (ablation)SMAGA · 4D-DressPSNR: 22.06 -> 27.89Improved
lengthen velocity window from 11 to 15 (ablation)SMAGA · 4D-DressPSNR: 27.89 -> 26.78Hurt
add SMAD module (40k nodes) (ablation)SMAGA · 4D-DressPSNR: 24.29 -> 27.89Improved
increase graph nodes from 40k to 100k (ablation)SMAD · 4D-DressPSNR: 27.89 -> 27.02Hurt
use GNN instead of MLP deformer (ablation)SMAD · 4D-Dress test motionsPSNR: 25.46 -> 27.89Improved
proposed SMAD vs vanilla GNN deformer (ablation)SMAGA · 4D-Dress test motionsPSNR: 28.68 -> 27.89Mixed
add velocity encoding on 30s dynamic sequence (ablation)SMAGA · 4D-Dress long sequencePSNR: 24.47 -> 25.65Improved
SMAGA vs best baseline on loose clothing novel poseSMAGA · 4D-Dress subject 00148PSNR: 22.79 -> 24.74Improved
SMAGA vs best baseline on novel pose, subject 00190SMAGA · 4D-Dress subject 00190LPIPS: 0.0278 -> 0.0347Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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