AI Paper Atlas

Research map / Image generation / Super-resolution

Spatially-Variant Degradation Model for Dataset-free Super-resolution

SHAOJIE GUO, Haofei Song, Qingli Li, Yan Wang

ECCV 2024 · Image generation › Super-resolution · approach: Blind super-resolution · 4 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
use spatially-variant degradation (5 atom kernels) instead of a single spatially-invariant kernel (ablation)SVDSR · Manga109 x2PSNR: 29.23 -> 29.89Improved
increase number of atom kernels beyond 5 (ablation)SVDSR · Set5 x2PSNR: 33.51 -> 33.43 -> 33.27 (N_D 5 -> 7 -> 9)Hurt
add instance normalization layer to the generator (ablation)SVDSR · Set14 x2PSNR: 29.28 -> 29.61Improved
add FFT-based frequency-domain skip connection (ablation)SVDSR · Set14 x2PSNR: 29.52 -> 29.61Improved
add frequency-domain likelihood term (ablation)SVDSR · Set14 x2PSNR: 29.61 -> 29.61No clear effect
spatially-variant model versus BSRDM at scale x4SVDSR · Set14 x4PSNR: 26.63 -> 26.81Improved
spatially-variant model versus BSRDM at scale x2SVDSR · Urban100 x2PSNR: 25.46 -> 26.40Improved
supply ground-truth kernel (non-blind) instead of estimating it (ablation)SVDSR · Set5 x2PSNR: 33.51 -> 34.44Improved
per-pixel kernel estimation versus BSRDMSVDSR · Set5 x2, 256x256runtime: 30s -> 33sNo clear effect

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