AI Paper Atlas

Research map / Image generation / Image restoration

Non-Local Intrinsic Decomposition With Near-Infrared Priors

Ziang Cheng, Yinqiang Zheng, Shaodi You, Imari Sato

ICCV 2019 · Image generation › Image restoration · approach: Pansharpening and spectral fusion · 37 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 global reflectance energy (ablation)RGB local · NIR-RGB testsetAavg LMSE (x1000): 76.2 -> 62.5Improved
add global reflectance energy (ablation)RGB local · NIR-RGB testsetAavg MSE (x1000): 87.7 -> 57.0Improved
add NIR input and NIR shading prior (ablation)RGB local · NIR-RGB testsetAavg LMSE (x1000): 76.2 -> 58.4Improved
add NIR input and NIR shading prior (ablation)RGB local · NIR-RGB testsetAavg MSE (x1000): 87.7 -> 52.2Improved
add global reflectance energy (ablation)NIR local · NIR-RGB testsetAavg LMSE (x1000): 58.4 -> 53.4Improved
add global reflectance energy (ablation)NIR local · NIR-RGB testsetAavg MSE (x1000): 52.2 -> 40.5Improved
add NIR input and NIR shading prior (ablation)RGB global · NIR-RGB testsetAavg LMSE (x1000): 62.5 -> 53.4Improved
add NIR input and NIR shading prior (ablation)RGB global · NIR-RGB testsetAavg MSE (x1000): 57.0 -> 40.5Improved
use convolution-based global energy instead of clustering sparsity constraintGehler et al. · NIR-RGB testsetAavg LMSE (x1000): 80.0 -> 62.5Improved
use convolution-based global energy instead of clustering sparsity constraintGehler et al. · NIR-RGB testsetAavg MSE (x1000): 52.0 -> 57.0Hurt
relax i = s + r with a posterior term instead of vanilla Colour RetinexColour Retinex · NIR-RGB testsetAavg LMSE (x1000): 144 -> 76.2Improved
use NIR-assisted energy instead of Colour RetinexColour Retinex · NIR-RGB testsetBavg LMSE (x1000): 7.50 -> 7.03Improved

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