Improvement of stereo matching algorithm for 3D surface reconstruction

作者：

Highlights：

•

• This article introduces an improved stereo matching algorithm for 3D surface reconstruction.

• The algorithm framework is developed using the standard local-based method.

• There are three contributions. First, the matching cost computation utilized the gradient based matching technique using a fixed window.

• Then, the ASW based on iterative Guided Filter is introduced at cost aggregation to filter the preliminary data.

• A new filtering approach at the last stage is presented which is to refine the final disparity map.

摘要

•This article introduces an improved stereo matching algorithm for 3D surface reconstruction.•The algorithm framework is developed using the standard local-based method.•There are three contributions. First, the matching cost computation utilized the gradient based matching technique using a fixed window.•Then, the ASW based on iterative Guided Filter is introduced at cost aggregation to filter the preliminary data.•A new filtering approach at the last stage is presented which is to refine the final disparity map.

论文关键词：3D reconstruction,Adaptive support weight,Gradient matching,Guided filter,Stereo matching

论文评审过程：Received 4 January 2018, Revised 8 March 2018, Accepted 3 April 2018, Available online 11 April 2018, Version of Record 14 April 2018.

论文官网地址：https://doi.org/10.1016/j.image.2018.04.001