AI Paper Atlas

Research map / 3D vision / Face and shape

Eyeglasses 3D shape reconstruction from a single face image

Yating Wang, Quan Wang, Feng Xu

ECCV 2020 · 3D vision › Face and shape · approach: 3D morphable face model regression · 2 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 joint training of glasses landmarks and segmentation (ablation)U-Net feature extractor · Glasses landmark detectionlandmark L2 error: 0.8701 -> 0.8378Improved
add joint training of glasses landmarks and segmentation (ablation)U-Net feature extractor · Glasses segmentationdice coefficient: 0.7801 -> 0.8183Improved
add physical nose-pad contact constraint to glasses pose estimation (ablation)glasses pose estimation · qualitative pose examples (Fig. 6)pose plausibilityImproved
add the constraint on rotation y,z and translation x of glasses relative to face (ablation)glasses pose estimation · qualitative pose examples (Fig. 6)pose plausibilityImproved
compare against single-image frontal method [28] on its test setproposed system · test set of [28]dice coefficient: 0.7306 vs 0.6885No clear effect
evaluate on extreme head poses and diverse glasses styles instead of frontal facesproposed system · own test setdice coefficient: 0.6885 -> 0.5552Hurt

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