AI Paper Atlas

Research map / Detection and segmentation / CNN features

RF-Net: An End-To-End Image Matching Network Based on Receptive Field

Xuelun Shen, Cheng Wang, Xin Li, Zenglei Yu, Jonathan Li, Chenglu Wen, Ming Cheng, Zijian He

CVPR 2019 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 114 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
use RF-Net instead of L2-Net+ORBlocal feature matching pipeline · HP-illumaverage match score: 0.705 -> 0.783Improved
use RF-Net instead of L2-Net+ORBlocal feature matching pipeline · HP-viewaverage match score: 0.673 -> 0.808Improved
use RF-Net instead of Hard-Net+SURFlocal feature matching pipeline · EFaverage match score: 0.334 -> 0.453Improved
replace LF-Det with RF-Det (ablation)LF-Det+LF-Des pipeline · HP-illumaverage match score: 0.617 -> 0.720Improved
replace LF-Det with RF-Det (ablation)LF-Det+LF-Des pipeline · HP-viewaverage match score: 0.566 -> 0.665Improved
replace LF-Det with RF-Det (ablation)LF-Det+LF-Des pipeline · EFaverage match score: 0.251 -> 0.325Improved
replace LF-Des with RF-Des (ablation)LF-Det+LF-Des pipeline · HP-illumaverage match score: 0.617 -> 0.744Improved
replace LF-Des with RF-Des (ablation)LF-Det+LF-Des pipeline · HP-viewaverage match score: 0.566 -> 0.714Improved
replace LF-Des with RF-Des (ablation)LF-Det+LF-Des pipeline · EFaverage match score: 0.251 -> 0.361Improved
add the neighbor mask to descriptor loss (ablation)RF-Net · HP-illumaverage match score: 0.734 -> 0.783Improved
add the neighbor mask to descriptor loss (ablation)RF-Net · HP-viewaverage match score: 0.753 -> 0.808Improved
add the neighbor mask to descriptor loss (ablation)RF-Net · EFaverage match score: 0.423 -> 0.453Improved

Later papers that compared with this method

2 later accepted papers report RFNet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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