AI Paper Atlas

Research map / 3D vision / Face and shape

Feed-Forward One-Shot Animatable Textured Mesh Avatar Reconstruction

Yisheng He

CVPR 2026 · 3D vision › Face and shape · approach: Gaussian and implicit head 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
replace per-vertex colors with a UV texture map (ablation)MeshLAM · VFHQ testPSNR: 18.09 -> 25.23Improved
add iterative GRU decoding instead of direct regression (ablation)MeshLAM · VFHQ testPSNR: 23.08 -> 25.23Improved
add texture-space reprojection and unwrapping (ablation)MeshLAM · VFHQ testFID: 29.428 -> 22.699Improved
add part-aware deformation clipping (ablation)MeshLAM · VFHQ testFID: 32.405 -> 22.699Improved
add optional UNet neural renderer (ablation)MeshLAM · VFHQ testPSNR: 23.180 -> 25.233Improved
use 2 GRU iterations instead of 1 (ablation)MeshLAM · VFHQ testPSNR: 23.10 -> 25.23Improved
use 3 GRU iterations instead of 2 (ablation)MeshLAM · VFHQ testmixed PSNR/LPIPS/FID: PSNR 25.23 -> 25.38; FID 22.699 -> 23.431Mixed
initialize Gaussian LAM with MeshLAM mesh instead of FLAMELAM · VFHQ testLPIPS: 0.077 -> 0.050Improved
mesh representation (8K vertices) instead of GaussiansMeshLAM vs LAM · reconstruction speedseconds: 5.8 -> 0.7Improved

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