AI Paper Atlas

Research map / Image generation / Image restoration

Reconstruct Anything Model a lightweight foundation model for computational imaging

Matthieu Terris, Samuel Hurault, Maxime Song, Julián Tachella

ICLR 2026 · Image generation › Image restoration · approach: Diffusion-based universal restoration · 0 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 proximal estimation input block (ablation)DRUNet backbone · Training tasks (10^4 iterations)PSNR (dB): 25.83 -> 26.64Improved
add conditioning of inner feature maps on y (ablation)DRUNet + prox · Training tasks (10^4 iterations)PSNR (dB): 26.64 -> 26.71Improved
add Krylov subspace blocks applying A^T A to features (ablation)DRUNet + prox + embed y · Training tasks (10^4 iterations)PSNR (dB): 26.71 -> 27.61Improved
train on all three tasks instead of inpainting only (evaluated on inpainting) (ablation)RAM-style model · Validation, inpaintingPSNR (dB): 30.84 -> 30.73No clear effect
train on all three tasks instead of deblurring only (evaluated on deblurring) (ablation)RAM-style model · Validation, deblurringPSNR (dB): 25.62 -> 25.58No clear effect
add proposed operator conditioning to DRUNet backbone (ablation)DRUNet · CBSD68 motion blur sigma=0.05PSNR (dB): 22.46 -> 26.47Improved
swap DRUNet backbone for PromptIR backbone (ablation)unconditioned backbone · CBSD68 motion blur sigma=0.05PSNR (dB): 22.46 -> 22.42No clear effect
use RAM instead of DRUNet for self-supervised finetuning on one imageself-supervised finetuning · Sentinel-2 compressed sensing, N=1PSNR (dB): 19.44 -> 30.40Improved
increase finetuning set from N=1 to N=100 imagesRAM self-supervised · Sentinel-2 compressed sensingPSNR (dB): 30.40 -> 33.57Improved
self-supervised instead of supervised finetuning (N=1)RAM · Sentinel-2 compressed sensingPSNR (dB): 30.77 -> 30.40No clear effect
tie weights across unrolled iterations instead of untieduDPIR · fastMRI multi-coil x8PSNR (dB): 33.71 -> 36.06Improved
use RAM zero-shot instead of UNet on multi-coil MRIUNet baseline · fastMRI multi-coil x8PSNR (dB): 28.50 -> 35.62Improved

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