atlas

Research map / 3D vision / Face and shape

ImFace: A Nonlinear 3D Morphable Face Model With Implicit Neural Representations

CVPR 2022 · 3D vision › Face and shape · approach: 3D morphable face model regression · 65 citations (OpenAlex)

Check 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
Use disentangled identity and expression deformation fields instead of one shared field (ablation)ImFace · FaceScape test setChamfer (mm): 0.772 -> 0.625Helped
Use disentangled identity and expression deformation fields instead of one shared field (ablation)ImFace · FaceScape test setF-score@0.001: 82.70 -> 91.11Helped
Use Neural Blend-Field instead of parameter-matched vanilla MLPs (ablation)ImFace · FaceScape test setChamfer (mm): 0.767 -> 0.625Helped
Use Neural Blend-Field instead of parameter-matched vanilla MLPs (ablation)ImFace · FaceScape test setF-score@0.001: 82.37 -> 91.11Helped
Assign expression embeddings to individual non-neutral scans rather than expression categories (ablation)ImFace · FaceScape test setChamfer (mm): 0.705 -> 0.625Helped
Assign expression embeddings to individual non-neutral scans rather than expression categories (ablation)ImFace · FaceScape test setF-score@0.001: 86.98 -> 91.11Helped

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