AI Paper Atlas

Research map / 3D vision / Face and shape

Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency

Jiaxiang Shang, Tianwei Shen, Shiwei li, Lei Zhou, Mingmin Zhen, Tian Fang, Long Quan

ECCV 2020 · 3D vision › Face and shape · approach: 3D morphable face model regression · 138 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
add multi-view geometry consistency losses to 2D feature losses (ablation)face reconstruction network · AFLW2000-3D yaw 60-90NME: 4.31 -> 3.76Improved
add multi-view losses (ablation)face network · AFLW2000-3D meanNME: 3.45 -> 3.20Improved
add pixel consistency loss with covisible map (ablation)baseline · MICC Florence cooperativeRMSE (mm): 1.83 -> 1.80Improved
add depth consistency loss with covisible map (ablation)baseline · MICC Florence cooperativeRMSE (mm): 1.83 -> 1.77Improved
add epipolar loss (ablation)baseline · MICC Florence outdoorRMSE (mm): 1.81 -> 1.77Improved
add epipolar loss (ablation)baseline · MICC Florence indoorRMSE (mm): 1.82 -> 1.81No clear effect
add pixel and depth losses together (ablation)baseline with covisible map · MICC Florence indoorRMSE (mm): 1.82 -> 1.81No clear effect
add covisible map to pixel+depth+epipolar losses (ablation)MGCNet · MICC Florence cooperativeRMSE (mm): 1.80 -> 1.73Improved
add covisible map (ablation)MGCNet · MICC Florence outdoorRMSE (mm): 1.82 -> 1.75Improved
add all multi-view losses and covisible map (ablation)baseline · MICC Florence cooperativeRMSE (mm): 1.83 -> 1.73Improved
use MGCNet instead of Deng et al.3D face reconstruction · MICC Florence cooperativeRMSE (mm): 1.83 -> 1.73Improved
use MGCNet instead of PRNface alignment · AFLW2000-3D meanNME: 3.62 -> 3.20Improved

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