AI Paper Atlas

Research map / 3D vision / Depth and stereo

Face Anything: 4D Face Reconstruction from Any Image Sequence

Umut Kocasarı, Simon Giebenhain, Richard Shaw, Matthias Niessner

ECCV 2026 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 2 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
predict canonical maps instead of motion to canonical space (ablation)Face Anything · NeRSembleEPE(2D): 6.210 -> 3.271Improved
sample both cameras and timestamps instead of fixed timestamp (static training) (ablation)Face Anything · NeRSembleEPE(2D): 3.864 -> 3.271Improved
sample both cameras and timestamps instead of fixed camera (monocular training) (ablation)Face Anything · NeRSemble 16-view depthAbsRel (x10): 0.064 -> 0.015Improved
sample both cameras and timestamps instead of fixed camera (monocular training) (ablation)Face Anything · NeRSembleEPE(2D): 3.031 (monocular training) vs 3.271 (full)Hurt
add DAViD facial pretraining to DA3 (ablation)DA3 · NeRSembleAbsRel monocular (x10): 0.085 -> 0.061Improved
add multi-view finetuning with canonical head on top of DAViD pretraining (ablation)DAViD Pretrained · NeRSemble 16 viewsAbsRel (x10): 0.033 -> 0.015Improved
use multiple input images instead of a single imageFace Anything · NeRSembledepth errorImproved
canonical map prediction vs V-DPM motion-based methodFace Anything · Efficiencyruntime (s): 160 -> 5Improved
Face Anything vs P3DMM on hair regionsFace Anything · NeRSemble 2D correspondence margin 2EPE(2D): 5.550 -> 1.838Improved
Face Anything vs V-DPMFace Anything · VFHQ margin 5CCE mean: 0.797 -> 0.398Improved
Face Anything vs Pi3 and Sapiens-1B on Ava-256 video depthFace Anything · Ava-256 monocular depthRMSE (x10): 0.081 -> 0.067 (best baseline Sapiens-2B)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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