AI Paper Atlas

Research map / Image generation / Image restoration

CIE XYZ Net: Unprocessing Images for Low-Level Computer Vision Tasks

Mahmoud Afifi, Abdelrahman Abdelhamed, Abdullah Abuolaim, Abhijith Punnappurath, Michael S. Brown

TPAMI 2021 · Image generation › Image restoration · approach: Image harmonization and color transformation · 52 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
learn CIE XYZ decomposition instead of standard gamma mappingsRGB to XYZ · MIT-Adobe FiveK testPSNR (dB): 21.84 -> 29.66Improved
use CIE XYZ Net instead of UPIsRGB to XYZ · MIT-Adobe FiveK testPSNR (dB): 22.19 -> 29.66Improved
use two-part global plus residual local network instead of U-Net (ablation)sRGB to XYZ · MIT-Adobe FiveK testPSNR (dB): 20.05 -> 29.66Improved
use two-part network instead of U-Net (ablation)Rec. XYZ to sRGB · MIT-Adobe FiveK testPSNR (dB): 43.39 -> 43.82Improved
denoise CBM3D in our XYZ instead of standard XYZCBM3D · SIDD-ValidationPSNR (dB): 33.84 -> 35.49Improved
denoise CBM3D in our XYZ instead of sRGBCBM3D · SIDD-ValidationPSNR (dB): 34.44 -> 35.49Improved
denoise DnCNN-P in our XYZ instead of standard XYZDnCNN-P · SIDD-ValidationPSNR (dB): 26.23 -> 27.71Improved
use our XYZ instead of standard XYZ for retrained DnCNNDnCNN-R · SIDD-ValidationPSNR (dB): 33.92 -> 33.00Hurt
use our XYZ instead of standard XYZ for retrained DnCNNDnCNN-R · SIDD-ValidationSSIM: 0.7833 -> 0.8865Improved
deblur in our XYZ space instead of sRGBKrishnan and Fergus deblurring · FiveK 244 imagesPSNR (dB): 29.41 -> 30.26Improved
deblur in our XYZ space instead of standard XYZKrishnan and Fergus deblurring · FiveK 244 imagesPSNR (dB): 28.68 -> 30.26Improved
add our reconstructed raw-like images to real training datailluminant estimation · NUS Canon EOS-1Ds Mark IIImean angular error: 4.15 -> 2.41Improved

Later papers that compared with this method

1 later accepted paper reports CIE XYZ Net 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