AI Paper Atlas

Research map / Image generation / Image restoration

Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration

Luwei Tu, Jiawei Wu, Xing Luo, Zhi Jin

ICML 2026 · Image generation › Image restoration · approach: Diffusion-based universal restoration · 0 citations (OpenAlex)

Read the paper

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 uncertainty-aware path schedule instead of OT schedule pi(u)=I (ablation)UDBM-L · All-in-One averagePSNR: 32.31 -> 32.61Improved
use adaptive path schedule instead of pi(u)=0.5I (ablation)UDBM-L · All-in-One averagePSNR: 32.02 -> 32.61Improved
add adaptive shared bridge term instead of constant 1.5 lambda_b (ablation)UDBM-L · All-in-One averagePSNR: 31.62 -> 32.61Improved
add terminal relaxation term (ablation)UDBM-L · All-in-One averagePSNR: 30.72 -> 32.61Improved
use uncertainty-adaptive relaxation instead of fixed 1.5I (ablation)UDBM-L · All-in-One averagePSNR: 32.12 -> 32.61Improved
use residual-based estimator instead of BayesCap (ablation)UDBM-L · All-in-One averagePSNR: 32.46 -> 32.61Improved
use residual-based estimator instead of heteroscedastic regression (ablation)UDBM-L · All-in-One averagePSNR: 32.04 -> 32.61Improved
use UDBM-M instead of HOGformerUDBM-M · All-in-One averagePSNR: 31.57 -> 31.60Improved
use UDBM-L instead of BioIR on denoisingUDBM-L · BSD68PSNR: 31.34 -> 31.40Improved
use UDBM-L instead of NAFNetUDBM-L · GoProPSNR: 33.69 -> 33.87Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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