AI Paper Atlas

Research map / Image generation / Image restoration

Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration

Jingwen He, Chao Dong, Yu Qiao

ECCV 2020 · Image generation › Image restoration · approach: Efficient restoration architectures · 58 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 global controllable residual connection (ablation)CResMD · CBSD68 blur r0.5 noise sigma0PSNR: 52.70 -> 53.17Improved
add global controllable residual connection (ablation)CResMD · CBSD68 blur r1 noise sigma0PSNR: 38.04 -> 38.38Improved
add global controllable residual connection (ablation)CResMD · LIVE1 blur r0.5 noise sigma0PSNR: 51.22 -> 52.21Improved
add global controllable residual connection (ablation)CResMD · CBSD68 blur r0 noise sigma0 (identity)PSNR: 71.39 -> +infImproved
increase number of local controllable residual connections from 1 to 32 (ablation)CResMD · CBSD68 2D modulationPSNR distance: sharp leap 0.22dB in deblurring r1 from 4 to 8 connectionsImproved
increase local connections from 1 to 32 on denoising (ablation)CResMD · CBSD68 denoising sigma15 and sigma50PSNR distance: less than 0.1dBNo clear effect
use beta sampling alpha=0.5 beta=1.0 instead of uniform (ablation)CResMD · LIVE1 sampling curvetotal PSNR: +0.28Improved
use beta sampling alpha=0.2 beta=1.0 instead of uniform (ablation)CResMD · LIVE1 sampling curvetotal PSNR: -0.50Hurt
use beta sampling alpha=1.0 beta=2.0 instead of uniform (ablation)CResMD · LIVE1 sampling curvetotal PSNR: +0.07Mixed
use CResMD instead of DNI/AdaFM/CFSNet on single-degradation deblurringCResMD · CBSD68 deblurring r2 to r4PSNR distance: >1.0 dBImproved

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