AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Optimal Transport for Unsupervised Denoising Learning

Wei Wang, Fei Wen, Zeyu Yan, Peilin Liu

TPAMI 2022 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 44 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 minimum-distance transport term to adversarial training (1/lambda 0 to 30) (ablation)OT denoising · Gaussian sigma=15, KODAK24PSNR: 29.97 -> 33.99Improved
raise 1/lambda from 1 to 10 (ablation)OT denoising · Gaussian sigma=15, KODAK24PSNR: 31.44 -> 32.85Improved
raise 1/lambda from 30 to 100 (ablation)OT denoising · Gaussian sigma=15, KODAK24PSNR: 33.99 -> 30.97Hurt
unsupervised OT criterion instead of supervised N2C on spatially correlated noiseOT denoising · Brown Gaussian noise, KODAK24PSNR: 31.86 -> 32.08Improved
unsupervised OT criterion instead of supervised N2C on Gaussian noiseOT denoising · Gaussian sigma=15, KODAK24PSNR: 34.92 -> 33.99Hurt
unsupervised OT criterion instead of BM3DOT denoising · Brown Gaussian noise, KODAK24PSNR: 29.20 -> 32.08Improved
unsupervised OT criterion instead of N2C on perceptual qualityOT denoising · Gaussian sigma=15, KODAK24PI: 2.41 -> 2.06Improved
unsupervised OT criterion instead of N2C on depth noise sigma=50OT denoising · Middlebury depth sigma=50PSNR: 34.88 -> 34.43Hurt
unsupervised OT criterion instead of N2C on microscopyOT denoising · FMD microscopyPSNR: 35.28 -> 35.73Improved
use clean images from another microscopy dataset instead of averaged images (ablation)OT denoising · FMD microscopyPSNR: 35.73 -> 34.49Hurt
unsupervised OT criterion instead of CGAN on microscopyOT denoising · FMD microscopyPSNR: 31.79 -> 35.73Improved

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