AI Paper Atlas

Research map / 3D vision / Face and shape

MoFA: Model-Based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction

Ayush Tewari, Michael Zollhofer, Hyeongwoo Kim, Pablo Garrido, Florian Bernard, Patrick Perez, Christian Theobalt

ICCV 2017 · 3D vision › Face and shape · approach: 3D morphable face model regression · 400 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 landmark surrogate loss (AlexNet) (ablation)MoFA · real data validationlandmark error (px): 5.3 -> 3.7Improved
add landmark surrogate loss (VGG-Face) (ablation)MoFA · real data validationlandmark error (px): 4.9 -> 3.4Improved
add landmark surrogate loss (AlexNet) (ablation)MoFA · real data validationphotometric error: 0.075 -> 0.078No clear effect
add landmark surrogate loss (VGG-Face) (ablation)MoFA · real data validationphotometric error: 0.073 -> 0.078No clear effect
add landmark surrogate loss (ablation)MoFA · Facewarehouse (9 identities)geometric error (mm): 1.9mm -> 1.7mmImproved
add landmark surrogate loss (ablation)MoFA · Facewarehouse (9 identities)landmark error (px): 5.0px -> 3.2pxImproved
add landmark surrogate loss (ablation)MoFA · Facewarehouse (9 identities)photometric error: 0.065 -> 0.068Hurt
use VGG-Face encoder instead of AlexNet (ablation)MoFA · real data validationlandmark error (px): 5.3 -> 4.9Improved
use VGG-Face encoder instead of AlexNet (ablation)MoFA · real data validationphotometric error: 0.075 -> 0.073Improved
unsupervised training on synthetic dataMoFA (AlexNet) · synthetic ground truthgeometric error (mm): 21.6mm -> 4.5mmImproved
unsupervised training on synthetic dataMoFA (AlexNet) · synthetic ground truthlandmark error (px): 31.6 -> 3.9Improved
use analytic model-based decoder instead of learned convolutional decoder (ablation)MoFA · qualitative (Fig. 14)image fidelityImproved

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