AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Physics-Guided Face Relighting Under Directional Light

Thomas Nestmeyer, Jean-Francois Lalonde, Iain Matthews, Andreas Lehrmann

CVPR 2020 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 128 citations (OpenAlex)

Check 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 physics-guided intrinsic decomposition and non-diffuse residual refinement instead of pix2pixFace relighting model · Face relighting test, with source illuminationDSSIM: .1832 -> .1618Improved
Use physics-guided intrinsic decomposition and non-diffuse residual refinement instead of pix2pixFace relighting model · Face relighting test, without source illuminationDSSIM: .2076 -> .1763Improved
Remove explicit access to source illumination (ablation)Ours · Face relighting testDSSIM: .1618 -> .1763Hurt
Train with DSSIM rather than L1 loss (ablation)Ours · Validation face relightingDSSIM: .1484 -> .1270Improved
Train with DSSIM rather than L2 loss (ablation)Ours · Validation face relightingDSSIM: .1547 -> .1270Improved
Train with LPIPS rather than DSSIM loss (ablation)Ours · Validation face relightingLPIPS: .2008 -> .1701Hurt
Add image and lighting intensity scaling augmentation (ablation)Training data · Face relightingunspecifiedNo 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