XFeat: Accelerated Features for Lightweight Image Matching | VitaVision
PaperCVPR · 2024

XFeat: Accelerated Features for Lightweight Image Matching

Guilherme PotjeFelipe CadarAndré AraujoRenato MartinsErickson R. Nascimento
arXiv 2404.19174DOIView in graph
1page built on it
1more page cites it
2narratives
0registry papers cite it

In the Atlas

ModelPrimary source of
XFeat

Lightweight CNN that jointly detects keypoints, extracts 64-D dense descriptors, and refines semi-dense matches from coarse descriptor pairs, targeting CPU-grade inference on hardware-constrained devices.

Cited as a reference by 1 page, grouped by domain

Features 1
LoFTR

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 · 0
’18’19’20’21’22’23’24SuperPoint: Self-Supervised Interest Point Detection and Description (2018)
Built upon by · 0