atlas

Research map / 3D vision / Face and shape

i3DMM: Deep Implicit 3D Morphable Model of Human Heads

CVPR 2021 · 3D vision › Face and shape · approach: 3D morphable face model regression · 122 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 i3DMM instead of FLAME for full-head fittingi3DMM · Full headChamfer (mm): 7.83 -> 3.31Helped
use i3DMM instead of FLAME for full-head fittingi3DMM · Full headF-score: 45.96 -> 63.38Helped
use i3DMM instead of BFM for face color fittingi3DMM · FaceColor: 0.09 -> 0.07Helped
replace landmark-based sampling with uniform sampling (ablation)i3DMM · FaceChamfer (mm): 1.0143 -> 1.1065Hurt
replace landmark-based sampling with uniform sampling (ablation)i3DMM · FaceColor: 0.0655 -> 0.0734Hurt
add sparse pairwise landmark supervision (ablation)i3DMM · FaceChamfer (mm): 0.9775 -> 1.0143Hurt
add sparse pairwise landmark supervision (ablation)i3DMM · FaceColor: 0.0681 -> 0.0655Mixed
jointly train the color and geometry networks (ablation)i3DMM · FaceColor: 0.0796 -> 0.0655Helped
jointly train the color and geometry networks (ablation)i3DMM · FaceChamfer (mm): 1.0319 -> 1.0143Helped

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