AI Paper Atlas

Research map / Image generation / Image restoration

Reflectance Adaptive Filtering Improves Intrinsic Image Estimation

Thomas Nestmeyer, Peter V. Gehler

CVPR 2017 · Image generation › Image restoration · approach: Pansharpening and spectral fusion · 62 citations (OpenAlex)

Check 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
Train a dense reflectance CNN directly with WHDR-Hinge loss rather than relying on pairwise classification and a globalization stepDirect CNN on IIW · IIW test splitWHDR: 19.5Improved
Apply bilateral filtering with flat guidance to the CNN reflectanceDirect CNN · IIW test splitWHDR: 19.49 -> 18.1Improved
Apply guided filtering with flat guidance to the CNN reflectanceDirect CNN · IIW test splitWHDR: 19.49 -> 17.7Improved
Apply guided filtering with flat guidanceZoran et al. 2015 · IIW test splitWHDR: 17.85 -> 16.38Improved
Apply the guided filter repeatedly, up to three applications, with flat guidanceZoran et al. 2015 · IIW test split of Zoran et al. 2015WHDR: down to 15.78 after three applicationsImproved
Filter CNN reflectance using the input image as bilateral guidanceDirect CNN · IIW test splitWHDR: 19.5 -> 18.9Improved
Filter CNN reflectance using the input image as guided-filter guidanceDirect CNN · IIW test splitWHDR: 19.5 -> 19.2Improved
Replace the CNN with its L1-flattened guidance image as the reflectance prediction (ablation)Direct CNN · IIW test splitWHDR: 19.5 -> 20.9Hurt
Increase convolution kernel size beyond 1x1 (ablation)Direct CNN · IIW validation setWHDRNo clear effect
Use larger kernel sizes (ablation)Direct CNN · IIW validation setWHDRHurt
Use alternative layouts without skip connections or a U-net, PReLU activations, or dilated convolutions (ablation)Direct CNN · IIW validation setWHDRNo clear effect
Augment pairwise labels with transitive-closure comparisons (ablation)Direct CNN training · IIW test set evaluated on original comparisonsWHDRNo clear effect

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