AI Paper Atlas

Research map / Image generation / Super-resolution

FRAMER: Frequency-Aligned Self-Distillation with Adaptive Modulation Leveraging Diffusion Priors for Real-World Image Super-Resolution

Seungho Choi, Jeahun Sung, Jihyong Oh

CVPR 2026 · Image generation › Super-resolution · approach: Diffusion-based super-resolution · 2 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 frequency-specific contrastive self-distillation instead of MSE distillation (ablation)DiT4SR (RealSR) · RealSRMANIQA: 0.467 -> 0.533Improved
add frequency decomposition to MSE distillation (ablation)DiT4SR (RealSR) · RealSRMUSIQ: 68.11 -> 65.74Hurt
use final layer as teacher instead of a random layer (ablation)FRAMER · RealSRMANIQA: 0.469 -> 0.533Improved
use random-layer negative instead of previous-layer negative (ablation)FRAMER · RealSRPSNR: 22.23 -> 23.04Improved
add InterCL for HF alongside IntraCL for LF (ablation)FRAMER · RealSRMUSIQ: 65.92 -> 69.01Improved
assign InterCL to LF and IntraCL to HF (reversed) (ablation)FRAMER · RealSRMANIQA: 0.533 -> 0.484Hurt
add FAW (adaptive weights) (ablation)FRAMER contrastive distillation · RealSRMUSIQ: 69.01 -> 70.50Improved
add FAM (alignment gating) (ablation)FRAMER contrastive distillation · RealSRPSNR: 23.04 -> 23.06No clear effect
add both FAW and FAM (ablation)FRAMER contrastive distillation · RealSRMUSIQ: 69.01 -> 72.24Improved
apply FRAMER to DiT4SR (DiT)DiT4SR · DrealSRPSNR: 23.64 -> 24.73Improved
apply FRAMER to PiSA-SR (U-Net)PiSA-SR · RealSRNIQE: 5.902 -> 5.513Improved
apply FRAMER to PiSA-SR (U-Net)PiSA-SR · RealLR200NIQE: 4.410 -> 4.381No clear effect

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