AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Fast Multi-Image Matching via Density-Based Clustering

Roberto Tron, Xiaowei Zhou, Carlos Esteves, Kostas Daniilidis

ICCV 2017 · Learning theory and algorithms › Clustering · approach: Clustering approximation algorithms · 50 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 QuickMatch multi-image clustering instead of pairwise matchingSIFT matching · Graffiti grafAUC: 58.8 -> 86.7Improved
use QuickMatch instead of pairwise matchingSIFT matching · Graffiti bikesAUC: 72.1 -> 95.3Improved
use QuickMatch instead of pairwise matchingSIFT matching · Graffiti ubcAUC: 87.4 -> 95.7Improved
use QuickMatch instead of MatchALSmulti-image matching · Graffiti grafAUC: 84.3 -> 86.7Improved
use QuickMatch instead of MatchALSmulti-image matching · Graffiti datasetcomputation time: 34.9 to 62.2 times fasterImproved
use QuickMatch instead of Spectralmulti-image matching · Graffiti datasetAUC: 3.2 to 17.9 percentage pointsImproved
use QuickMatch instead of pairwise matchingSIFT matching, 500-600 features per image · SfM datasetsprecisionImproved
increase extracted features to tens of thousandsQuickMatch · SfM datasetsprecision vs pairwiseNo clear effect
use QuickMatch instead of pairwise matching with deep hypercolumn featuresFG3DCar left-view sedans (37 images) · FG3DCarpercentage of annotated pointsImproved

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