广东工业大学学报2025，Vol.42Issue(3)：92-100,9.DOI:10.12052/gdutxb.250027
J-SuperPoint:基于差分信息的关键点检测方法
J-SuperPoint:Keypoint Detection Method Based on Differential Information
摘要
Abstract
Addressing the time-consuming issue of mainstream keypoint detection algorithms,a novel keypoint detection and description method is proposed.First,the rotating pixel difference convolution module is designed to symmetrically sample differential information from images.This module is further extended to implement the judger module that integrates sampled differential and convolutional information,effectively extracting features from the raw image.Finally,shared encoder and lightweight decoder,which coordinates information between decoders,are designed,while improving the loss function to construct an efficient encoder-decoder network model.Experimental results demonstrate that the proposed method maintains favorable real-time performance while achieving high computational accuracy,providing a solution that balances real-time capability and precision for applications such as image matching and visual localization.关键词
计算机视觉/特征分析/图像匹配Key words
computer vision/feature analysis/image matching分类
信息技术与安全科学引用本文复制引用
谢仕烁,肖泽辉,陶杰..J-SuperPoint:基于差分信息的关键点检测方法[J].广东工业大学学报,2025,42(3):92-100,9.基金项目
国家自然科学基金资助项目(U23A20390,62276069) （U23A20390,62276069）
广东省基础与应用基础研究基金自然科学基金资助项目(2024B1515020094) （2024B1515020094）
