Distinctive Image Features from Scale-Invariant Keypoints | VitaVision
PaperInternational Journal of Computer Vision · 2004

Distinctive Image Features from Scale-Invariant Keypoints

David Lowe
DOIView in graph
4pages built on it
5more pages cite it
4narratives
10registry papers cite it

In the Atlas

ConceptPrimary source of
Feature Descriptors

Fixed-length vectors encoding the local image appearance around a keypoint, built so the same physical point yields similar descriptors across views — the basis for descriptor matching.

ConceptPrimary source of
Feature Matching

Establishing keypoint correspondences between two images by comparing descriptors and resolving them into a consistent partial assignment — from the ratio test to learned optimal-transport matchers.

ConceptPrimary source of
Image Pyramid

A discrete multi-resolution representation — a sequence of images at progressively coarser resolution, each smoothed and downsampled from its predecessor.

AlgorithmPrimary source of
SIFT: Scale-Invariant Feature Transform

Detects keypoints as scale-space extrema in a Difference-of-Gaussian image pyramid, refines location and scale by 3D quadratic interpolation, assigns canonical orientation from local gradient histograms, and emits a 128-D descriptor invariant to scale, rotation, and moderate affine and illumination change.

Cited as a reference by 5 pages, grouped by domain

Features 4
BRIEF: Binary Robust Independent Elementary FeaturesLightGlueORB: Oriented FAST and Rotated BRIEFSURF: Speeded Up Robust Features
Detection 1
HOG: Histograms of Oriented Gradients

Appears in 4 narratives

NarrativeDetection, Removing the MachineryNarrativeThe Geometry Pipeline CollapsesNarrativeVision Under a Latency BudgetNarrativeWhere Did the Inductive Bias Go?

Lineage

Papers in the Atlas registry only · one dot per paper
Built upon by · 10
’88’89’90’91’92’93’94’95’96’97’98’99’00’01’02’03’04’05’06’07’08’09’10’11’12’13’14’15’16’17’18’19’20’21’22’23Histograms of Oriented Gradients for Human Detection (2005)SURF: Speeded Up Robust Features (2006)BRIEF: Binary Robust Independent Elementary Features (2010)Object Detection with Discriminatively Trained Part-Based Models (2010)ORB: An efficient alternative to SIFT or SURF (2011)Structure-from-Motion Revisited (2016)Feature Pyramid Networks for Object Detection (2017)SuperGlue: 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)A Combined Corner and Edge Detector (1988)