AI Paper Atlas

Research map / Image generation / Image restoration

Learning Distortion Invariant Representation for Image Restoration From a Causality Perspective

Xin Li, Bingchen Li, Xin Jin, Cuiling Lan, Zhibo Chen

CVPR 2023 · Image generation › Image restoration · approach: Priors for restoration networks · 25 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 DIL instead of ERMRRDB image denoising · CBSD68, noise level 30 (unseen)PSNR: 24.90 -> 30.29Improved
Use parallel sampling instead of serial sampling (ablation)DIL image denoising with first-order optimization · CBSD68, noise level 30 (unseen)PSNR: 30.29 -> 29.92Hurt
Use second-order instead of first-order optimization with serial sampling (ablation)DIL image denoising · CBSD68, noise level 30 (unseen)PSNR: 30.29 -> 27.48Hurt
Use parallel sampling and second-order optimization (ablation)DIL image denoising · CBSD68, noise level 30 (unseen)PSNR: 30.29 -> 29.14Hurt
Apply DIL instead of ERMRRDB image denoising · Kodak24, noise level 50 (unseen)PSNR: 19.02 -> 27.76Improved
Use DIL with serial sampling and second-order optimization (ablation)RRDB image denoising · Manga109, noise level 30 (unseen)PSNR: 26.62 -> 26.02Hurt
Apply DIL instead of ERMRRDB image deblurring · Set5, blur level 5.0 (unseen)PSNR: 22.00 -> 23.46Improved
Apply DIL instead of ERMRRDB hybrid distortion removal · Urban100, mild distortion (unseen)PSNR: 23.97 -> 25.00Improved
Apply DIL instead of ERMRRDB real image super-resolution · RealSR V3 (unseen)PSNR: 27.65 -> 27.94Improved
Use parallel sampling and second-order optimization instead of serial sampling and first-order optimization (ablation)DIL real image super-resolution · RealSR V3 (unseen)PSNR: 27.94 -> 28.12Improved
Apply DIL to the SwinIR backbone instead of ERMSwinIR image denoising · CBSD68, noise level 30 (unseen)PSNR: 24.22 -> 29.08Improved
Apply DIL with D2 rather than ERM with D2 augmentationRRDB real image super-resolution · RealSR V3 (unseen)PSNR: 27.39 -> 27.65Improved

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