AI Paper Atlas

Research map / 3D vision / Face and shape

Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation

Haiwen Feng, Timo Bolkart, Joachim Tesch, Michael J. Black, Victoria Abrevaya

ECCV 2022 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering · 28 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 synthetic-data semi-supervised training instead of self-supervised only (ablation)faceSH · FAIR benchmarktotal score: 35.62 -> 21.31Improved
add scene consistency loss (ablation)fuseSH · FAIR benchmarkbias score: 11.08 -> 3.50Improved
add scene consistency loss (ablation)fuseSH · FAIR benchmarkavg ITA error: 15.22 -> 15.82No clear effect
add scene consistency loss (ablation)fuseSH · FAIR benchmarkMAE: 17.02 -> 20.37Hurt
add light-intensity conditioning of albedo encoder (ablation)fuseSH · FAIR benchmarkavg ITA error: 15.22 -> 14.16Improved
add light-intensity conditioning of albedo encoder (ablation)fuseSH · FAIR benchmarkbias score: 11.08 -> 6.56Improved
add conditioning to fuseSH + sc (full model) (ablation)fuseSH + sc · FAIR benchmarktotal score: 19.32 -> 16.81Improved
add scene consistency to fuseSH + cond (full model) (ablation)fuseSH + cond · FAIR benchmarkbias score: 6.56 -> 2.63Improved
use scene-level light intensity (fuseSH) instead of crop-only light, semi-supervised (ablation)faceSH + semi · FAIR benchmarktotal score: 21.31 -> 26.31Hurt
use balanced albedo model instead of BFM albedo space (ablation)TRUST · FAIR benchmarkavg ITA error: 16.19 -> 13.87Improved
use balanced albedo model instead of BFM albedo space (ablation)TRUST · FAIR benchmarkbias score: 15.33 -> 2.79Improved
use balanced albedo model instead of AlbedoMM (ablation)TRUST · FAIR benchmarktotal score: 33.00 -> 16.67Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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