AI Paper Atlas

Research map / Image generation / Image restoration

Multiscale Structure Guided Diffusion for Image Deblurring

Mengwei Ren, Mauricio Delbracio, Hossein Talebi, Guido Gerig, Peyman Milanfar

ICCV 2023 · Image generation › Image restoration · approach: Diffusion-based universal restoration · 119 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 multiscale structure guidance to image-conditioned diffusion (ablation)icDPM-L · Realblur-J out-of-domainLPIPS: 0.156 -> 0.128Improved
increase icDPM diffusion network size from 6M to 27M without guidance (ablation)icDPM · Realblur-J out-of-domainLPIPS: 0.150 -> 0.156Hurt
increase icDPM diffusion network size from 6M to 27M without guidance (ablation)icDPM · GoPro in-domainPSNR: 30.555 -> 32.105Improved
use smaller guidance network (Guide-S) instead of Guide-L (ablation)icDPM-L with guidance · Realblur-J out-of-domainLPIPS: 0.123 -> 0.128No clear effect
inject guidance in latent space instead of input-level concatenation (ablation)guidance network · Realblur-JLPIPS: 0.145 -> 0.143Improved
use multiscale guidance (x2, x4, x8) instead of single scale (ablation)guidance network · Realblur-JLPIPS: 0.143 -> 0.141Improved
use grayscale regression target instead of RGB (ablation)guidance network · Realblur-JLPIPS: 0.141 -> 0.137Improved
inject guidance by addition instead of concatenation or adaptive norm (ablation)icDPM · GoProPSNR: 30.248 / 29.676 -> 31.139Improved
add regression loss on guidance features (ablation)Ours · GoProPSNR: 30.56 -> 31.19Improved
keep input concatenation alongside guidance (ablation)Ours · GoPro in-domainPSNR: 25.20 -> 30.65Improved
add adversarial domain adaptation on guidance featuresOurs · Realblur-Jvisual qualityHurt
use guided icDPM instead of regression and GAN baselines on average of four test setsdeblurring · Average over GoPro, HIDE, Realblur-J, REDSLPIPS: 0.133 -> 0.104Improved

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