AI Paper Atlas

Research map / Image generation / Super-resolution

ReAL: Reference-to-Image (R2I) Aware Latent Diffusion for Image Super-Resolution

Byeonghun Lee, Hyunmin Cho, Sunghoon Im, Kyong Hwan Jin

ECCV 2026 · Image generation › Super-resolution · approach: Perceptual and real-world SR

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 the LR-latent concatenation path (ablation)ReAL · SR x4 ablationPSNR: 26.689 -> 27.352Improved
add the LR-latent concatenation path (ablation)ReAL · SR x4 ablationLPIPS: 0.309 -> 0.246Improved
add reference conditioning (ablation)ReAL · SR x4 ablationSSIM: 0.799 -> 0.803Improved
add reference conditioning (ablation)ReAL · SR x4 ablationLPIPS: 0.250 -> 0.246Improved
add reference conditioning (ablation)ReAL · SR x4 ablationPSNR: 27.084 -> 27.352Hurt
add the Reference Fusion Module (ablation)ReAL · SR x4 ablationPSNR: 26.837 -> 27.352Improved
add the Reference Fusion Module (ablation)ReAL · SR x4 ablationMUSIQ: 61.802 -> 61.565Mixed
use a properly retrieved reference instead of a random one (ablation)ReAL · SR x4 ablationSSIM: 0.780 -> 0.803Improved
use a properly retrieved reference instead of a random one (ablation)ReAL · SR x4 ablationLPIPS: 0.263 -> 0.246Improved
increase reference database from 30% to 100% (ablation)ReAL · RealSRMUSIQ: 61.240 -> 66.529Improved
use external CUFED database instead of in-domain database (ablation)ReAL · RealSRPSNR: 21.044 -> 21.060No clear effect
use learned hashing instead of VGG retrieval (ablation)ReAL · reference matchingmatching cost (ms): 3830 ms -> 62 msImproved

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