AI Paper Atlas

Research map / 3D vision / Face and shape

GeoDiff4D: Geometry-Aware Diffusion for 4D Head Avatar Reconstruction

Chao Xu, Xiaochen Zhao, Xiang Deng, Jingxiang Sun, Donglin Di, Zhuo Su, Yebin Liu

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 cross-view pairing to expression encoder training (ablation)GeoDiff4D VGM · NeRSemblev2 self-reenactmentPSNR: 19.895 -> 21.586Improved
add joint image-normal representation (ablation)GeoDiff4D VGM · NeRSemblev2 self-reenactmentPSNR: 20.809 -> 21.586Improved
add Domain-Spatial attention (ablation)GeoDiff4D VGM · NeRSemblev2 self-reenactmentPSNR: 20.984 -> 21.586Improved
add synthetic SynthHuman data to training (ablation)GeoDiff4D VGM · NeRSemblev2 self-reenactmentPSNR: 20.892 -> 21.586Improved
add hierarchical refinement in avatar reconstruction (ablation)GeoDiff4D reconstruction · NeRSemblev2 self-reenactmentPSNR: 19.816 -> 19.953Improved
add surface normal regularization (ablation)GeoDiff4D reconstruction · NeRSemblev2 self-reenactmentAED: 2.713 -> 2.563Improved
use video-generated normals instead of DAViD monocular normals (ablation)GeoDiff4D reconstruction · NeRSemblev2 self-reenactmentPSNR: 19.947 -> 19.953No clear effect
GeoDiff4D versus CAP4D baselineGeoDiff4D · NeRSemblev2 self-reenactmentPSNR: 19.295 -> 19.951Improved

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