AI Paper Atlas

Research map / Image generation / Image restoration

A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising

Jun Xu, Lei Zhang, David Zhang

ECCV 2018 · Image generation › Image restoration · approach: Raw and low-light noise modeling · 296 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 weight matrix W2 (per-patch noise weights) to the data-fidelity term (TWSC vs WSC), AWGN sigma=15 (ablation)WSC · AWGN sigma=15, 20 grayscale imagesPSNR (dB): 32.06 -> 32.34Improved
add weight matrix W2 (TWSC vs WSC), AWGN sigma=75 (ablation)WSC · AWGN sigma=75, 20 grayscale imagesPSNR (dB): 24.54 -> 25.15Improved
add weight matrix W2 (TWSC vs WSC) (ablation)WSC · Real-world noisy images, 15 cropped (Dataset 2)PSNR (dB): 37.36 -> 37.81Improved
add weight matrix W2 (TWSC vs WSC) (ablation)WSC · Real-world noisy images, 15 cropped (Dataset 2)SSIM: 0.9516 -> 0.9586Improved
add weight matrix W2 (TWSC vs WSC) (ablation)WSC · DND benchmark, 1000 cropped real-world imagesPSNR (dB): 36.81 -> 37.94Improved
add weight matrix W2 (TWSC vs WSC) (ablation)WSC · DND benchmark, 1000 cropped real-world imagesSSIM: 0.9165 -> 0.9403Improved
use TWSC instead of MCWNNMreal-world denoising · DND benchmark, 1000 cropped real-world imagesPSNR (dB): 37.38 -> 37.94Improved
use TWSC instead of MCWNNMreal-world denoising · Real-world noisy images, 15 cropped (Dataset 2)PSNR (dB): 37.70 -> 37.81Improved
use TWSC instead of discriminatively trained DnCNN on AWGNAWGN denoising · AWGN sigma=15, 20 grayscale imagesPSNR (dB): 32.59 -> 32.34No clear effect
use TWSC instead of DnCNN on real noiseDnCNN · DND benchmark, 1000 cropped real-world imagesPSNR (dB): 32.41 -> 37.94Improved
use TWSC instead of Neat Image (speed)Neat Image · DND, time per 512x512 imageruntime (s): 1.1 -> 195.2Hurt
add weight matrix W2 (TWSC vs WSC) runtime cost (ablation)WSC · DND, time per 512x512 imageruntime (s): 188.6 -> 195.2No 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