AI Paper Atlas

Research map / 3D vision / Face and shape

DiFaReli: Diffusion Face Relighting

Puntawat Ponglertnapakorn, Nontawat Tritrong, Supasorn Suwajanakorn

ICCV 2023 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering · 56 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
use Modulator network with rendered shading reference instead of concatenating reference to DDIM input (ablation)DiFaReli · Multi-PIE ablationLPIPS: 0.0868 -> 0.0789Improved
use spatial shading reference instead of non-spatial light vector (ablation)DiFaReli · Multi-PIE ablationDSSIM: 0.0885 -> 0.0670Improved
add shape, camera and identity non-spatial conditions (ablation)DiFaReli · Multi-PIE ablationLPIPS: 0.0909 -> 0.0789Improved
add shape and camera conditioning (ablation)DiFaReli · Multi-PIE ablationMSE: 0.0063 -> 0.0077Mixed
add ArcFace identity embedding conditioning (ablation)DiFaReli · Multi-PIE ablationLPIPS: 0.0847 -> 0.0789Improved
add background image conditioning (ablation)DiFaReli · qualitativebackground preservationImproved
use DiFaReli instead of Hou et al. (CVPR'22) with same-subject target lightingMulti-PIE · Multi-PIE (same subject)LPIPS: 0.1622 -> 0.1370Improved
use DiFaReli with different-subject target lightingMulti-PIE · Multi-PIE (different subject)DSSIM: 0.1000 -> 0.0969Improved

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