AI Paper Atlas

Research map / Image generation / Image restoration

GLoSH: Global-Local Spherical Harmonics for Intrinsic Image Decomposition

Hao Zhou, Xiang Yu, David W. Jacobs

ICCV 2019 · Image generation › Image restoration · approach: Image harmonization and color transformation · 54 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 synthetic SUNCG pre-training (ablation)GLoSH · IIWWHDR (%): 17.82 -> 15.20Improved
add synthetic SUNCG pre-training (ablation)GLoSH · NYUv2mean angular error: 35.14 -> 25.57Improved
add synthetic SUNCG pre-training (ablation)GLoSH · SAWAP (%): 88.52 -> 95.01Improved
add self-supervised pseudo-label loss (ablation)GLoSH · IIWWHDR (%): 15.50 -> 15.20Improved
add self-supervised pseudo-label loss (ablation)GLoSH · NYUv2mean angular error: 25.93 -> 25.57Improved
add self-supervised pseudo-label loss (ablation)GLoSH · SAWAP (%): 95.79 -> 95.01Hurt
add symmetric WHDR loss L_R2 (ablation)GLoSH · SAWAP (%): 91.89 -> 95.01Improved
add symmetric WHDR loss L_R2 (ablation)GLoSH · IIWWHDR (%): 15.34 -> 15.20Improved
add second fine scale to one-scale model (ablation)GLoSH · IIWWHDR (%): 18.70 -> 16.62Improved
add third scale to two-scale model (ablation)GLoSH · IIWWHDR (%): 16.62 -> 15.20Improved
add non-negative lighting constraint (ablation)GLoSH coarse net · SUNCG valnegative-lighting global SH (%): 13.39% -> 1.09%Improved
add global-local SH with coarse-to-fine net vs RGB-D baselineGLoSH · NYUv2 shadingAP (%): 90.38% -> 95.43%Improved

Later papers that compared with this method

1 later accepted paper reports GLoSH as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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