Learning accurate template matching with differentiable coarseto-fine correspondence refinement

作     者：Zhirui Gao Renjiao Yi Zheng Qin Yunfan Ye Chenyang Zhu Kai Xu 

作者机构：College of ComputerNational University of Defense TechnologyChangsha 410073China 

出 版 物：《Computational Visual Media》 (计算可视媒体（英文版）)

年 卷 期：2024年第10卷第2期

页      面：309-330页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 080203[工学-机械设计及理论] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported in part by the National Key R&D Program of China(2018AAA0102200) the National Natural Science Foundation of China(62002375,62002376,62325221,62132021) 

主　　题：template matching differentiable homography structure-awareness transformers 

摘      要：Template matching is a fundamental task in computer vision and has been studied for *** plays an essential role in manufacturing industry for estimating the poses of different parts,facilitating downstream tasks such as robotic *** methods fail when the template and source images have different modalities,cluttered backgrounds,or weak *** also rarely consider geometric transformations via homographies,which commonly exist even for planar industrial *** tackle the challenges,we propose an accurate template matching method based on differentiable coarse-tofine correspondence *** use an edge-aware module to overcome the domain gap between the mask template and the grayscale image,allowing robust *** initial warp is estimated using coarse correspondences based on novel structure-aware information provided by *** initial alignment is passed to a refinement network using references and aligned images to obtain sub-pixel level correspondences which are used to give the final geometric *** evaluation shows that our method to be significantly better than state-of-the-art methods and baselines,providing good generalization ability and visually plausible results even on unseen real data.