AI Paper Atlas

Research map / Image generation / Super-resolution

Feature Super-Resolution: Make Machine See More Clearly

CVPR 2018 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 66 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Apply feature super-resolution (FSR-GAN) to low-resolution query features instead of raw featuresVGG16 retrieval features · Oxford5K/Paris/Holidays retrieval at 1/64 scaleretrieval precision: +25%Helped
Enhance features with FSR-GAN at 1/64 downscaleVGG16 features · Feature distance to high-res featureEuclidean distance: 0.62Helped
Use pixel-space image super-resolution (SRCNN, VDSR) instead of FSR-GANquery images · Oxford5K, Paris, Holidays retrievalmAPMixed
Decrease query image resolution (down-sampling ratio) without enhancementraw VGG16 features · Oxford5K retrievalmAPHurt
Add distractor Flickr100k images to the databaseFSR-GAN retrieval · Oxford5K/Paris/Holidays + Flickr100kmAPNo clear effect
Lower resolution of query on HolidaysFSR-GAN · HolidaysmAPNo 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