AI Paper Atlas

Research map / Image generation / Image restoration

Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image Restoration

Theo Joseph Adrai, Guy Ohayon, Michael Elad, Tomer Michaeli

NeurIPS 2023 · Image generation › Image restoration · approach: Diffusion-based universal restoration · 3 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
apply latent optimal transport (alpha=0) to pre-trained modelSwinIR · SISR x4FID: 2.54 -> 1.39Improved
apply latent optimal transport (alpha=0)Swin2SR · SR x4 + JPEG q=10FID: 205.00 -> 183.80Improved
apply latent optimal transport (alpha=0)ESRGAN · SISR x4FID: 1.06 -> 0.89Improved
apply latent optimal transport (alpha=0)DDRM · SR x4 + AWGN sigma=50FID: 36.44 -> 29.71Improved
apply latent optimal transport (alpha=0)NLM denoiser · AWGN sigma=50FID: 12.84 -> 14.88Hurt
apply latent optimal transport (alpha=0)SwinIR · SISR x4PSNR: 28.10 -> 25.48Hurt
interpolate with alpha=0.9 toward originalSwinIR · SISR x4PSNR: 28.10 -> 28.15Improved
use alpha outside [0,1], e.g. alpha in [1,2]Swin2SR · SR x4 + JPEG q=10FID: 183.80 -> 168.12Improved
use patch size p=3 or 5 vs p=1 in latent unfolding (ablation)Latent transport · SISR x4 ESRGANPSNR and FIDImproved
larger patch sizes 7<=p<=15 (ablation)Latent transport · SISR x4 ESRGANPSNRHurt
vary training sample count S from 10^2 to 10^5 (ablation)Latent transport · SISR x4 ESRGANall metricsNo clear effect
compute distribution parameters from paired images (ablation)Latent transport · SISR x4 ESRGANPSNR and FIDMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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