AI Paper Atlas

Research map / 3D vision / Face and shape

Zero-Shot Reconstruction of Animatable 3D Avatars with Cloth Dynamics from a Single Image

Joohyun Kwon, Geonhee Sim, Gyeongsik Moon

CVPR 2026 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 0 citations (OpenAlex)

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 Dynamic Transformer (ablation)DynaAvatar · 4D-Dress (ablation)PSNR: 22.57 -> 23.62Improved
add Dynamic Transformer (ablation)DynaAvatar · 4D-Dress (ablation)SSIM: 0.952 -> 0.958Improved
add Dynamic Transformer (ablation)DynaAvatar · 4D-Dress (ablation)LPIPS: 0.068 -> 0.062Improved
add static-to-dynamic knowledge transfer with LoRA (vs training Static Transformer from scratch) (ablation)DynaAvatar · DNA-Rendering / 4D-Dress (qualitative)texture preservationImproved
add LoRA (vs full fine-tuning of pretrained Static Transformer) (ablation)DynaAvatar · DNA-Rendering / 4D-Dress (qualitative)texture preservationImproved
add DynaFlow loss (ablation)DynaAvatar · DNA-Rendering / 4D-Dress (qualitative)cloth motion and boundary qualityImproved
fully reannotate dataset with accurate SMPL-X fits (vs original annotations) (ablation)DynaAvatar · 4D-DressPSNR: 20.72 -> 23.74Improved
reannotate only originally available frames (vs original annotations) (ablation)DynaAvatar · 4D-DressPSNR: 20.72 -> 20.91No clear effect
reannotate all frames rather than only available frames (ablation)DynaAvatar · 4D-DressPSNR: 20.91 -> 23.74Improved
use DynaAvatar instead of LHMsingle-image avatar · DNA-RenderingPSNR: 17.42 -> 19.45Improved
use DynaAvatar instead of IDOLsingle-image avatar · Actors-HQPSNR: 20.93 -> 21.38Improved
use DynaAvatar instead of LHMsingle-image avatar · DNA-Renderingface consistency: 0.697 -> 0.712Improved

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