AI Paper Atlas

Research map / 3D vision / Depth and stereo

GRAPE: Generalizable and Robust Multi-view Facial Capture

Jing Li, Di Kang, Zhenyu He

ECCV 2024 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 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
replace learned head localizer with visual hull (cross-camera-array) (ablation)TEMPEH global · FaMoS -> FaceScape, no finetuningaverage error (mm): 32.27 -> 8.06Improved
add visibility-aware 3D feature aggregation (ablation)TEMPEH + V.H. init. · FaMoS -> FaceScape, no finetuningaverage error (mm): 8.06 -> 7.20Improved
add update-by-disagreement training (ablation)TEMPEH + V.H. init. + vis. · FaMoS -> FaceScape, no finetuningaverage error (mm): 7.20 -> 2.43Improved
add update-by-disagreement training on noisy FaceScape (ablation)TEMPEH + V.H. init. + vis. · FaceScape same-arrayaverage error (mm): 2.54 -> 1.20Improved
replace learned localizer with visual hull on noisy FaceScape (ablation)TEMPEH global · FaceScape same-arrayaverage error (mm): 3.10 -> 2.53Improved
replace learned localizer with visual hull on clean FaMoS (ablation)TEMPEH global · FaMoS complete headaverage error (mm): 2.11 -> 2.38Hurt
add update-by-disagreement to local stage (GRAPE local vs TEMPEH local)TEMPEH local · FaMoS face regionaverage error (mm): 0.43 -> 0.44No clear effect
vary visibility margin rho (0.1, 0.05, 0) (ablation)GRAPE global · FaceScapeaverage error (mm): 1.20 / 1.25 / 1.23No clear effect
add visual hull init and visibility aggregation on FaceScape -> FaMoS (ablation)TEMPEH global · FaceScape -> FaMoS, no finetuningaverage error (mm): 32.26 -> 2.63Improved

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