atlas

Research map / 3D vision / Face and shape

RAFaRe: Learning Robust and Accurate Non-parametric 3D Face Reconstruction from Pseudo 2D&3D Pairs

AAAI 2023 · 3D vision › Face and shape · approach: 3D morphable face model regression · 9 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Train PRNet on pseudo 2D&3D pairs instead of original fitted data (ablation)PRNet · FaceScape-wild, 0°–5°CD: 2.61 -> 1.97Helped
Train PRNet on pseudo 2D&3D pairs instead of original fitted data (ablation)PRNet · FaceScape-wild, 60°–90°CD: 3.88 -> 6.93Hurt
Replace PIFu with the base SDF branch (ablation)Face reconstruction model · FaceScape-wild, 0°–5°CD: 2.14 -> 1.81Helped
Add the fine SDF branch (ablation)RAFaRe · FaceScape-wild, 0°–5°CD: 1.81 -> 1.79Helped
Add the fine SDF branch (ablation)RAFaRe · FaceScape-wild, 60°–90°CD: 5.04 -> 5.16Hurt
Add normal-map carving for small-scale geometry (ablation)RAFaRe · FaceScape-wild, 0°–5°MNE: 0.062 -> 0.058Helped
Add normal-map carving for small-scale geometry (ablation)RAFaRe · FaceScape-wild, 60°–90°CD: 5.16 -> 5.26Hurt
Use the complete pseudo-pair-trained, hierarchical SDF reconstruction methodFaceScape-wild · FaceScape-wild, 0°–5°CD: 2.61 -> 1.79Helped

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