SuperPoint: Self-Supervised Interest Point Detection and Description | VitaVision
PaperCVPR Workshop (Deep Learning for Visual SLAM) · 2018

SuperPoint: Self-Supervised Interest Point Detection and Description

Daniel DeToneTomasz MalisiewiczAndrew Rabinovich
arXiv 1712.07629DOIView in graph
1page built on it
5more pages cite it
2narratives
4registry papers cite it

In the Atlas

ModelPrimary source of
SuperPoint

Fully-convolutional CNN that jointly detects interest points and computes 256-D descriptors in a single forward pass, trained without human annotations via Homographic Adaptation on synthetic shapes and MS-COCO images.

Cited as a reference by 5 pages, grouped by domain

Features 5
Feature MatchingLightGlueLoFTRSuperGlueXFeat

Appears in 2 narratives

NarrativeThe Geometry Pipeline CollapsesNarrativeVision Under a Latency Budget

Lineage

Papers in the Atlas registry only · one dot per paper
Built upon by · 4
’06’07’08’09’10’11’12’13’14’15’16’17’18’19’20’21’22’23’24SuperGlue: Learning Feature Matching with Graph Neural Networks (2020)LoFTR: Detector-Free Local Feature Matching with Transformers (2021)LightGlue: Local Feature Matching at Light Speed (2023)XFeat: Accelerated Features for Lightweight Image Matching (2024)Machine Learning for High-Speed Corner Detection (2006)