AI Paper Atlas

Research map / Image generation / Super-resolution

FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution

Aro Kim, Myeongjin Jang, Chaewon Moon, Youngjin Shin, Jinwoo Jeong, Sang-hyo Park

CVPR 2026 · Image generation › Super-resolution · approach: Diffusion-based super-resolution · 1 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 LRRB and DAW to the one-step baseline (ablation)FiDeSR · DIV2KMUSIQ: 67.6043 -> 68.2869Improved
add LRRB (latent residual refinement) (ablation)FiDeSR without DAW · DIV2KMANIQA: 0.6278 -> 0.6285No clear effect
add DAW (ablation)FiDeSR without LRRB · DIV2KMANIQA: 0.6236 -> 0.6278No clear effect
add LRRB to baseline (ablation)baseline · HF noise prediction MSE (avg)MSE: 0.1048 -> 0.1032Improved
inject high-frequency components (strength 0.1 to 0.5) (ablation)FiDeSR · RealSRMANIQA / PSNR: MANIQA 0.6580 -> 0.6803; PSNR 26.2542 -> 25.5778Mixed
inject low-frequency components (strength 0.1 to 0.5) (ablation)FiDeSR · RealSRPSNR / MANIQA: PSNR 26.2542 -> 26.3448; MANIQA 0.6580 -> 0.6522Mixed
use FiDeSR rather than PiSA-SRPiSA-SR · RealSRFID: 124.18 -> 109.68Improved
use FiDeSR rather than PiSA-SR on DIV2KPiSA-SR · DIV2KMANIQA: 0.6375 -> 0.6384No clear effect
use FiDeSR rather than PiSA-SR on DRealSRPiSA-SR · DRealSRPSNR: 28.32 -> 28.90Improved

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