Homography-guided stereo matching for wide-baseline image interpolation  

作　　者：Yuan Chang Congyi Zhang Yisong Chen Guoping Wang 

机构地区：[1]Peking University,Beijing 100871,China [2]Beijiing Engineering Technology Research Center of Virtual Simulation and Visualization,Peking University,Beijing 100871,China [3]The University of Hong Kong,Hong Kong,China

出　　处：《Computational Visual Media》2022年第1期119-133,共15页计算可视媒体（英文版）

基　　金：supported by the National Key Technology Research and Development Program of China(No.2017YFB1002601);PKU-Baidu Fund(No.2019BD007);National Natural Science Foundation of China(NSFC)(No.61632003).

摘　　要：Image interpolation has a wide range of applications such as frame rate-up conversion and free viewpoint TV.Despite significant progresses,it remains an open challenge especially for image pairs with large displacements.In this paper,we first propose a novel optimization algorithm for motion estimation,which combines the advantages of both global optimization and a local parametric transformation model.We perform optimization over dynamic label sets,which are modified after each iteration using the prior of piecewise consistency to avoid local minima.Then we apply it to an image interpolation framework including occlusion handling and intermediate image interpolation.We validate the performance of our algorithm experimentally,and show that our approach achieves state-of-the-art performance.

关 键 词：image interpolation view synthesis homo-graphy propagation belief propagation 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]