AI Paper Atlas

Research map / Image generation / Image restoration

Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restoration

Jiahong Fu, Qi Xie, Deyu Meng, Zongben Xu

TPAMI 2024 · Image generation › Image restoration · approach: Priors for restoration networks · 28 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
replace standard convolution with F-Conv equivariant convolution in proximal network (ablation)Prox_CNN · Urban100 denoisingPSNR: 30.57 -> 31.05Improved
use PDO-eConv equivariant convolution instead of standard CNN (ablation)Prox_CNN · Urban100 denoisingPSNR: 30.57 -> 29.55Hurt
use G-CNN or E2-CNN equivariant convolution instead of standard CNN (ablation)Prox_CNN · Urban100 denoisingPSNR: 30.57 -> 30.75No clear effect
increase equivariant number t from 1 to 24 (ablation)Rotation equivariant CNN · DIV2Krelative equivariant error: 0.852 -> 0.068Improved
add rotation equivariant proximal network (p8+) to KXNetKXNet · Urban100 SR x4 (std 0)PSNR: 25.41 -> 25.69Improved
add rotation equivariant proximal network (p8+) to KXNet on out-of-distribution noiseKXNet · Urban100 SR x4 (std 50)PSNR: 21.83 -> 22.06Improved
use p8 (fewer channels, t=8) instead of p4 for KXNet (ablation)KXNet-p4 · Urban100 SR x4 (std 0)PSNR: 25.55 -> 25.30Hurt
add rotation equivariant proximal network (p8+) to ACDNetACDNet · DeepLesion MARPSNR: 41.44 -> 42.43Improved
add rotation equivariant proximal network (p8+) to DICDNetDICDNet · DeepLesion MARPSNR: 42.24 -> 43.52Improved
add rotation equivariant proximal network (p8+) to OSCNetOSCNet · DeepLesion MARPSNR: 42.21 -> 42.90Improved
use p8 instead of p4 for DICDNet (ablation)DICDNet-p4 · DeepLesion MARPSNR: 42.67 -> 42.48No clear effect
add rotation equivariant proximal network (p8+) to RCDNetRCDNet · Rain100HPSNR: 31.28 -> 31.81Improved

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