AI Paper Atlas

Research map / 3D vision / Depth and stereo

Deep Single-Image Portrait Relighting

Hao Zhou, Sunil Hadap, Kalyan Sunkavalli, David W. Jacobs

ICCV 2019 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 222 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 the illumination prediction loss branch (ablation)Our relighting model · Relighting validation set (Target)RMSE: 0.0460 -> 0.0435Improved
add the illumination prediction loss branch (ablation)Our relighting model · Relighting validation set (Target)RMSE-s: 0.0395 -> 0.0351Improved
add the illumination prediction loss branch (ablation)Our relighting model · Relighting validation set (Target)DSSIM: 0.0251 -> 0.0251No clear effect
add the self-supervision loss (ablation)Our relighting model · Relighting validation set (Target)RMSE: 0.0448 -> 0.0435Improved
add the self-supervision loss (ablation)Our relighting model · Relighting validation set (Target)DSSIM: 0.0258 -> 0.0251Improved
add the self-supervision loss (ablation)Our relighting model · Relighting validation set (Source reconstruction)RMSE: 0.0313 -> 0.0170Improved
add confidence learning (ablation)Our lighting estimation · Lighting estimationRMSE-s: 0.8231 -> 0.6633Improved
use our model instead of SfSNet for relightingsingle-image portrait relighting · Relighting validation set (Target)RMSE: 0.2397 -> 0.0435Improved
use our model instead of SIRFS for relightingsingle-image portrait relighting · Relighting validation set (Target)DSSIM: 0.0827 -> 0.0251Improved
use our model instead of lighting transfer baseline given ground-truth reference (oracle)lighting transfer · Relighting validation set (lighting transfer comparison)RMSE: 0.0406 -> 0.0435Mixed
use our model instead of lighting estimation baselineslighting estimation · Lighting estimationRMSE-s: 1.3252 -> 0.6633Improved

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