AI Paper Atlas

Research map / Image generation / Image restoration

PRISM: Controllable Diffusion for Compound Image Restoration with Scientific Fidelity

Rupa Kurinchi-Vendhan, Pratyusha Sharma, Antonio Torralba, Sara Beery

ICLR 2026 · Image generation › Image restoration · approach: Efficient restoration architectures

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
use selective instead of full restorationPRISM · Remote sensing downstreamaccuracy: 0.842 -> 0.836No clear effect
use selective instead of full restorationPRISM · Camera traps downstreamaccuracy: 0.976 -> 0.984Improved
use selective instead of full restorationPRISM · Microscopy downstreammIoU: 0.475 -> 0.580Improved
use selective instead of full restorationPRISM · Urban scenes downstreammIoU: 0.615 -> 0.650Improved
add denoising on top of super-resolutionPRISM · BioSR segmentationmIoU: 0.580 -> 0.475Hurt
restore with super-resolution instead of denoisingPRISM · BioSR fluorescenceMSE: 0.006 -> 0.018Hurt
restore with super-resolution instead of no restorationPRISM · BioSR segmentationmIoU: 0.356 -> 0.580Improved
train on compound degradations instead of primitives only (ablation)PRISM · MDB (1 to 4 distortions)PSNRImproved
add compound-aware contrastive CLIP fine-tuning (ablation)PRISM · MDB sequential vs composite promptingPSNRImproved
use PRISM instead of MPerceiverMDB · MDBFID: 48.18 -> 48.97Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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