AI Paper Atlas

Research map / Image generation / Image restoration

Intrinsic Image Decomposition Using Paradigms

David Alexander Forsyth, Jason Rock

TPAMI 2021 · Image generation › Image restoration · approach: Image harmonization and color transformation · 16 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 adversarial smoothing (ablation)BBA paradigm intrinsic decomposition · IIW simulated test setsWHDR: Without adversarial smoothing (NoSmo), performance is comparable to RetinexImproved
add averaging over more tiles and scales (ablation)Base paradigm method · IIW simulated test setsWHDR: N_t=7, N_sigma=3 (Base) -> N_t=15, N_sigma=5 (BBA)Improved
add discrete image averaging (ablation)BBAP · IIW simulated test setsWHDR: BBAF always reports a very much better WHDR than BBAImproved
use discrete image averaging instead of discrete tile averaging (ablation)BBAP · IIW simulated test setsWHDR: BBAF clearly better than BBATImproved
add postprocessing (ablation)BBA · IIW test (held-out threshold)WHDR: BBAP appears worse than BBA on standard test; BBAP almost always smaller WHDR on simulated setsMixed
use CGIntrinsics tiles instead of paradigm images (ablation)BBAF · IIW simulated test setsWHDR: outperformed by RetinexHurt
vary paradigm details (fragment sizes) (ablation)BBAF · IIW simulated test setsWHDRNo clear effect
use a dark shading paradigm (ablation)BBAF · IIW simulated test setsWHDRHurt
vary discriminator patch scale from 22x22 to 10x10, 29x29, 48x48 or 128x128 (ablation)BBAF · IIW simulated test setsWHDR: 22 x 22 best; SD 10 x 10, ID 29 x 29, MD 48 x 48, BD 128 x 128Mixed
add extra heads for thin and thick dark barsBBAF · IIW testWHDRHurt
choose models by single standard test WHDR vs many simulated test setsevaluation protocol · IIW simulated test setsWHDR std: standard deviation is 0.3% for the base methodMixed

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