AI Paper Atlas

Research map / 3D vision / Depth and stereo

Faces as Lighting Probes via Unsupervised Deep Highlight Extraction

Renjiao Yi, Chenyang Zhu, Ping Tan, Stephen Lin

ECCV 2018 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 43 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 unsupervised low-rank finetuning on real celebrity face images after synthetic pretraining (ablation)Highlight-Net · highlight removal on lab facesRMSE / SSIMImproved
use finetuned Highlight-Net instead of the strongest prior highlight removalHighlight-Net · synthetic facesmean RMSE: 4.15 -> 3.37Improved
use finetuned Highlight-Net instead of the strongest prior highlight removalHighlight-Net · real facesmean RMSE: 8.93 -> 7.61Improved
use finetuned Highlight-Net instead of the strongest prior highlight removalHighlight-Net · real facesmean SSIM: 0.89 -> 0.89No clear effect
use face-based non-parametric environment map instead of best prior illumination methodface lighting probe · diffuse bunny relighting, outdoorrelighting RMSE: 17.77 -> 10.78Improved
use face-based non-parametric environment map instead of best prior illumination methodface lighting probe · diffuse bunny relighting, indoorrelighting RMSE: 20.52 -> 13.18Improved
use face-based non-parametric environment map instead of best prior illumination methodface lighting probe · glossy bunny relighting, indoorrelighting RMSE: 21.01 -> 13.69Improved
use face-based method instead of best prior on real captured scenesface lighting probe · real scenes outdoornormalized RMSE: 0.154 -> 0.143Improved
use face-based method instead of best prior on real captured scenesface lighting probe · real scenes indoornormalized RMSE: 0.050 -> 0.045Improved
use ground-truth face positions instead of estimated ones for light triangulationface lighting probe · lamp 1 positionposition error (m): 0.41 -> 0.20Improved
use ground-truth face positions instead of estimated ones for light triangulationface lighting probe · lamp 2 positionposition error (m): 0.51 -> 0.49No clear effect

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