AI Paper Atlas

Research map / Image generation / Super-resolution

Bridging the Distribution Gap to Harness Pretrained Diffusion Priors for Super-Resolution

JoonKyu Park, Kyoung Mu Lee

ICLR 2026 · Image generation › Super-resolution · approach: Diffusion-based super-resolution

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 adaptive predicted timestep instead of a fixed timestep (ablation)DM-SR · RealSet80MUSIQ: 69.990 -> 70.616 (best fixed 250)Improved
use larger fixed timestep (500 vs 50) (ablation)DM-SR · RealSet80MUSIQ: 68.982 -> 69.078Improved
add adversarial loss to L1+perceptual (ablation)DM-SR · RealSet80MUSIQ: 64.153 -> 69.947Improved
add distribution matching loss alone (ablation)DM-SR · RealSet80MUSIQ: 64.153 -> 69.089Improved
add noise loss alone (ablation)DM-SR · RealSet80MUSIQ: 64.153 -> 69.189Improved
add Ldm and Leps on top of Ladv (ablation)DM-SR · RealSet80MUSIQ: 69.947 -> 70.616Improved
add Ldm on top of Ladv (ablation)DM-SR · RealSRLPIPS: 0.328 -> 0.317Improved
use LPIPS instead of L1 pixel distance as timestep ground truth (ablation)DM-SR timestep estimator · RealSet80MUSIQ: 70.328 -> 70.616Improved
use LPIPS instead of SSIM as timestep ground truth (ablation)DM-SR timestep estimator · RealSet80MUSIQ: 70.352 -> 70.616No clear effect
supervise timestep by min reconstruction error (min*) (ablation)DM-SR timestep estimator · RealSet80MUSIQ: 70.616 -> 65.630Hurt
increase sampling steps from 1 to 5 (ablation)DM-SR · RealSet80LIQE: 4.652 -> 4.773; MUSIQ 70.616 -> 69.948Mixed
increase sampling steps from 1 to 20 (ablation)DM-SR · RealSet80LIQE: 4.652 -> 4.152Hurt

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