ULMR: An Unsupervised Learning Framework for Mismatch Removal

ULMR: An Unsupervised Learning Framework for Mismatch Removal

Due to radiometric and geometric distortions between images, mismatches are inevitable. Thus, a mismatch removal process is required for improving matching accuracy. Although deep learning methods have been proved to outperform handcraft methods in specific scenarios, including image identification...

Full description

Bibliographic Details
Main Authors: Cailong Deng, Shiyu Chen, Yong Zhang, Qixin Zhang, Feiyan Chen
Format: Article
Language:English
Published: MDPI AG 2022-08-01
Series:Sensors
Subjects:
unsupervised learning
mismatch removal
reinforcement learning
policy gradient
expected reward
Online Access:https://www.mdpi.com/1424-8220/22/16/6110

Internet

https://www.mdpi.com/1424-8220/22/16/6110

Similar Items