AI Paper Atlas

Research map / Detection and segmentation / CNN features

Spatially-Varying Blur Detection Based on Multiscale Fused and Sorted Transform Coefficients of Gradient Magnitudes

S. Alireza Golestaneh, Lina J. Karam

CVPR 2017 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 110 citations (OpenAlex)

Check 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
fuse information from all tested scales instead of using a single scale (ablation)HiFST · Blur datasetprecision-recall performanceImproved
use HiFST instead of the compared state-of-the-art methodssingle-image spatially-varying blur detection · Blur datasetprecisionImproved
add zero-mean Gaussian noise with variances 0, 10^-5, and 10^-4 to the inputsHiFST · Blur datasetprecision-recall performanceNo clear effect
add zero-mean Gaussian noise with variances 10^-3 and 10^-2 to the inputsHiFST · Blur datasetprecision-recall performanceHurt

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