AI Paper Atlas

Research map / 3D vision / Face and shape

FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Arbitrary Images

Jianjiang Yao, Ke Xian, Renxiang Dai, Robert Qiu

ECCV 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
add motion refinement module (MARM) (ablation)FFAvatar · VFHQ novel expressions (few-shot, 8 inputs)PSNR: 23.20 -> 23.35Improved
add motion refinement module (MARM) (ablation)FFAvatar · VFHQ novel expressions (few-shot, 8 inputs)LPIPS: 0.088 -> 0.081Improved
add motion refinement module (MARM) (ablation)FFAvatar · VFHQ novel expressions (few-shot, 8 inputs)FPS: 468 -> 31Hurt
increase input frames from 1 to 8 (ablation)FFAvatar · VFHQ novel expressions, input countPSNR: 21.82 -> 23.35Improved
increase input frames from 8 to 32 (ablation)FFAvatar · VFHQ novel expressions, input countPSNR: 23.35 -> 23.38No clear effect
use sparse-to-dense instead of sparse-only (S-5K) (ablation)FFAvatar · Sparse-to-dense ablation (UV 128)PSNR: 19.69 -> 23.35Improved
use sparse-to-dense instead of direct dense optimization (D-20K) (ablation)FFAvatar · Sparse-to-dense ablation (UV 128)train time per 1000 iters: 120min -> 47minImproved
use sparse-to-dense instead of direct dense optimization (D-20K) (ablation)FFAvatar · Sparse-to-dense ablation (UV 128)PSNR: 23.41 -> 23.35No clear effect
direct dense optimization at UV 256 (D-64K) (ablation)FFAvatar · Sparse-to-dense ablation (UV 256)feasibilityHurt
FFAvatar vs GPAvatar few-shot on NeRSemble novel viewsFFAvatar · NeRSemble novel views (few-shot)LPIPS: 0.163 -> 0.098Improved
FFAvatar one-shot vs GAGAvatar/LAM PSNRFFAvatar · VFHQ novel expressions (one-shot)PSNR: 21.82 vs LAM 22.65Mixed

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