AI Paper Atlas

Research map / Image generation / Image restoration

Residual Diffusion Bridge Model for Image Restoration

Hebaixu Wang, Jing Zhang, Haoyang Chen, Haonan Guo, Di Wang, Jiayi Ma, Bo Du

CVPR 2026 · Image generation › Image restoration · approach: Diffusion-based universal restoration

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
modulate noise with residual pi = x0 - mu instead of pi = 1 (ablation)RDBM-L · Five-task averagePSNR: 30.15 -> 31.04Improved
modulate noise with residual instead of pi = 1 (ablation)RDBM-L · Low-light enhancementPSNR: 21.71 -> 24.53Improved
modulate noise with residual instead of pi = 1 (ablation)RDBM-L · DesnowingPSNR: 32.79 -> 32.59Mixed
use pi = 0 (flow-matching-like) instead of residual (ablation)RDBM-L · Five-task averagePSNR: 31.04 -> 28.21Hurt
use absolute residual instead of signed residual (ablation)RDBM-L · Five-task averagePSNR: 31.04 -> 30.94No clear effect
use cosine noise schedule instead of linear (ablation)RDBM-L · Five-task averagePSNR: 30.99 -> 31.04Improved
use cosine noise schedule instead of linear (ablation)RDBM-L · DesnowingPSNR: 34.15 -> 32.59Hurt
use stationary variance lambda 10/255 instead of 100/255 (ablation)RDBM-L · Five-task averagePSNR: 29.08 -> 31.04Improved
increase sampling steps from 10 to 100 NFE (ablation)RDBM-L · Five-task averagePSNR: 31.04 -> 30.19Hurt
increase sampling steps from 2 to 10 NFE (ablation)RDBM-L · Five-task averagePSNR: 22.81 -> 31.04Improved
scale RDBM from T to L variantRDBM · Five-task averagePSNR: 27.31 -> 31.04Improved
use RDBM instead of GOUB bridge on inpaintingRDBM · CelebA-HQ inpaintingPSNR: 31.56 -> 37.88Improved

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