VD-Matcher: A Very Deep Local Feature Matcher With Weight Recycling and Keypoint Detection

Establishing local feature matches between image pairs serves as a fundamental component of plentiful vision tasks, such as visual localization and Structure from Motion (SfM). Recently, detector-free techniques equipped with the transformer have exhibited exceptional performance. Theoretically, opt...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on circuits and systems for video technology 2025-11, Vol.35 (11), p.11416-11431
Main Authors:	Dai, Kun, Zhou, Zilong, Jiang, Zhiqiang, Sun, Qihao, Xie, Tao, Gao, Hongbo, An, Tao, Li, Ruifeng, Zhao, Lijun
Format:	Article
Language:	English
Subjects:	Accuracy Computer architecture Convolutional neural networks deep learning Feature extraction Local feature matching Matching Parameters Pipelines Recycling Source code Stacking Training transformer Transformers Visual tasks Visualization
Citations:	Items that this one cites
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!