AI Paper Atlas

Research map / Image generation / Image restoration

Cross-Camera Convolutional Color Constancy

Mahmoud Afifi, Jonathan T. Barron, Chloe LeGendre, Yun-Ta Tsai, Francois Bleibel

ICCV 2021 · Image generation › Image restoration · approach: Image harmonization and color transformation · 79 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 the gradient intensity histogram as input (ablation)C5 · Cube+ ablation (7 encoders, trained with augmentation)mean angular error: 2.30 -> 1.87Improved
add extra u,v coordinate channels (CoordConv) to histograms (ablation)C5 · Cube+ ablation (7 encoders, trained with augmentation)mean angular error: 2.03 -> 1.87Improved
add smoothness regularization on generated filters and bias (ablation)C5 · Cube+ ablation (7 encoders, trained with augmentation)mean angular error: 2.07 -> 1.87Improved
increase smoothness strength to lambda_B=0.25, lambda_F=1.85 (ablation)C5 · Cube+ ablation (7 encoders, trained with augmentation)mean angular error: 1.87 -> 2.23Hurt
increase batch size during training from 16 to 64 (ablation)C5 · Cube+ ablation (7 encoders, trained with augmentation)mean angular error: 1.93 -> 1.87Improved
add cross-camera data augmentation (ablation)C5 · Cube+ ablationmean angular error: 2.10 -> 1.87Improved
add cross-camera data augmentation (ablation)C5 · INTEL-TAU ablationmean angular error: 2.62 -> 2.49Improved
add six more unlabeled images from the test camera (m=1 to m=7) (ablation)C5 · Cube+ ablation (7 encoders, trained with augmentation)mean angular error: 2.60 -> 1.87Improved
use more additional images beyond m=7 (m=13) (ablation)C5 · Cube+ ablation (7 encoders, trained with augmentation)mean angular error: 1.87 -> 1.95No clear effect
raise histogram bin size from 16 to 64 (ablation)C5 · Cube+ ablation (7 encoders, trained with augmentation)mean angular error: 2.28 -> 1.87Improved
raise histogram bin size from 64 to 128 (ablation)C5 · Cube+ ablation (7 encoders, trained with augmentation)mean angular error: 1.87 -> 2.03Hurt
choose additional images as vivid instead of random (ablation)C5 · Cube+ Challengemean angular error: 2.24 -> 2.19Improved

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