← Search

Tzu-Han Wu

2 accepted papers

2023

LGCNet: Feature Enhancement and Consistency Learning Based on Local and Global Coherence Network for Correspondence Selection

ICRA 2023poster

Correspondence selection, a crucial step in many computer vision tasks, aims to distinguish between inliers and outliers from putative correspondences. The coherence of correspondences is often used for predicting inlier probability, but it is difficult for neural networks to extract coherence conte…

Cited by 6SourceScholar
2023

MUFeat: Multi-Level CNN and Unsupervised Learning for Local Feature Detection and Description

IROS 2023poster

Local feature detection and description are two essential steps in many visual applications. Most learned local feature methods require high-quality labeled data to achieve superior performance, but such labels are often expensive. To address this problem, we propose MUFeat, an unsupervised learning…

Cited by 1SourceScholar