AI Paper Atlas

Research map / Image generation / Image restoration

CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy

Dongyoung Kim, Mahmoud Afifi, Dongyun Kim, Michael S. Brown, Seon Joo Kim

ICCV 2025 · Image generation › Image restoration · approach: Image harmonization and color transformation · 14 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
condition on camera fingerprint embedding from calibrated CCMs instead of extra test-camera images (C5)CCMNet · Gehler-Shimean angular error: 2.36 -> 2.23Improved
use CCMNet instead of C5 (m=9)NUS-8 · NUS-8mean angular error: 2.54 -> 2.32Improved
use CCMNet instead of C5 on Cube+CCMNet · Cube+mean angular error: 1.87 -> 1.68Improved
remove need for additional test camera images; reduce model sizeCCMNet vs C5 · Gehler-Shimodel size (MB): 2.09 -> 1.05Improved
add camera fingerprint embedding (CFE) to SIIE backbone (ablation)SIIE · Cube+mean angular error: 3.39 -> 2.60Improved
add CFE to SIIE backbone on Gehler-Shi (ablation)SIIE · Gehler-Shimean angular error: 3.67 -> 3.62No clear effect
add imaginary camera augmentation plus CFE to SIIE (ablation)SIIE · Cube+mean angular error: 3.39 -> 1.91Improved
add CFE encoder to backbone (ablation)CCMNet · Gehler-Shimean angular error: 2.53 -> 2.23Improved
add CFE encoder without augmentation (ablation)CCMNet · Gehler-Shimean angular error: 2.79 -> 2.74No clear effect
use interpolated imaginary camera augmentation (0<=alpha<=1) instead of alpha=1 camera mapping (ablation)CCMNet · Cube+mean angular error: 1.86 -> 1.68Improved
add augmentation (alpha=1) without CFE on Gehler-Shi (ablation)backbone f · Gehler-Shimean angular error: 2.79 -> 2.87Hurt

Later papers that compared with this method

1 later accepted paper reports CCMNet 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