AI Paper Atlas

Research map / 3D vision / Face and shape

Unrestricted Facial Geometry Reconstruction Using Image-To-Image Translation

Matan Sela, Elad Richardson, Ron Kimmel

ICCV 2017 · 3D vision › Face and shape · approach: 3D morphable face model regression · 283 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
use the full image-to-image reconstruction pipeline vs best prior methodfacial geometry reconstruction · BU-3DFEmean depth error: 3.61 -> 3.51Improved
same comparison on spread of errorsfacial geometry reconstruction · BU-3DFEstd depth error: 2.99 -> 2.69Improved
same comparison at 90% errorfacial geometry reconstruction · BU-3DFE90% depth error: 6.82 -> 6.59Improved
compare per expression against best prior methodfacial geometry reconstruction · BU-3DFE by expressionmean depth error: happy 3.41 -> 3.01; surprise 4.00 -> 4.41Mixed
add geometric consistency loss from the network to GAN translationsynthetic-to-real GAN · synthetic face translationgeometry preservationImproved

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