AI Paper Atlas

Research map / 3D vision / Face and shape

DiFaReli++: Diffusion Face Relighting With Consistent Cast Shadows

Puntawat Ponglertnapakorn, Nontawat Tritrong, Supasorn Suwajanakorn

TPAMI 2025 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering

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 Modulator network for spatial shading-reference conditioning (ablation)DiFaReli · Multi-PIE ablationDSSIM: 0.0749 -> 0.0670Improved
use shading reference instead of light encoding as non-spatial vector (ablation)DiFaReli · Multi-PIE ablationDSSIM: 0.0885 -> 0.0670Improved
add s, cam and ArcFace xi non-spatial conditions (ablation)DiFaReli · Multi-PIE ablationDSSIM: 0.0713 -> 0.0670Improved
add DECA s and cam conditions (ablation)DiFaReli · Multi-PIE ablationMSE: 0.0063 -> 0.0077Hurt
add DECA s and cam conditions (ablation)DiFaReli · Multi-PIE ablationDSSIM: 0.0674 -> 0.0670Improved
add ArcFace xi condition (ablation)DiFaReli · Multi-PIE ablationDSSIM: 0.0686 -> 0.0670Improved
remove zero-conv block from ControlNet (CN-mod) (ablation)ControlNet + cross-attention · Multi-PIE conditioning alternativesDSSIM: 0.0983 -> 0.0697Improved
replace ControlNet spatial conditioning with DiFaReli++ Modulator (ablation)cross-attention non-spatial · Multi-PIE conditioning alternativesDSSIM: 0.0983 -> 0.0694Improved
replace cross-attention with DiFaReli++ non-spatial conditioning (ablation)DiFaReli++ spatial · Multi-PIE conditioning alternativesDSSIM: 0.0694 -> 0.0664Improved
add cast shadow map conditioning (DiFaReli++ over DiFaReli)DiFaReli · Multi-PIE (same subject as target lighting)DSSIM: 0.0711 -> 0.0604Improved
distill DiFaReli++ into single-shot networkDiFaReli++ · Multi-PIE (same subject as target lighting)DSSIM: 0.0604 -> 0.0590Improved
distill into single-shot network instead of multi-step DPM-Solver/UniPC samplingDiFaReli++ · Runtimeseconds: 0.07 seconds vs over one second at 10 steps; 13.56s at 100 stepsImproved

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