Learning accurate template matching with differentiable coarseto-fine correspondence refinement  

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

机构地区：[1]College of Computer,National University of Defense Technology,Changsha 410073,China

出　　处：《Computational Visual Media》2024年第2期309-330,共22页计算可视媒体（英文版）

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).

摘　　要：Template matching is a fundamental task in computer vision and has been studied for decades.It plays an essential role in manufacturing industry for estimating the poses of different parts,facilitating downstream tasks such as robotic grasping.Existing methods fail when the template and source images have different modalities,cluttered backgrounds,or weak textures.They also rarely consider geometric transformations via homographies,which commonly exist even for planar industrial parts.To tackle the challenges,we propose an accurate template matching method based on differentiable coarse-tofine correspondence refinement.We use an edge-aware module to overcome the domain gap between the mask template and the grayscale image,allowing robust matching.An initial warp is estimated using coarse correspondences based on novel structure-aware information provided by transformers.This 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 transformation.Extensive 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.

关 键 词：template matching differentiable homography structure-awareness TRANSFORMERS 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]