跳到主要导航 跳到搜索 跳到主要内容

A dense correspondences matching algorithm with hierarchical pyramid architecture

  • Beihang University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

We introduce a novel matching algorithm for computing dense pixel correspondences, which is inspired from deep convolutional neural networks. Whereas the prevailing approaches operate at the pixel level, we propose a hierarchical, multi-layer pyramid architecture that compute the match at multiple scales-ranging from an entire image, to coarse grid cells, to every atomic patch. The algorithm consists of two steps: in the bottom-up mode, calculate the similarity of patches between two images in different scales; in the top-down mode, aggregate the similarity from the top layer until the bottom. We evaluate the performance of our algorithm on the Mikolajczyk and Middlebury datasets. Our model shows excellent results in particular for repetitive textures as well as the varying illumination.

源语言英语
主期刊名Proceedings - 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2017
编辑Qingli Li, Lipo Wang, Mei Zhou, Li Sun, Song Qiu, Hongying Liu
出版商Institute of Electrical and Electronics Engineers Inc.
1-6
页数6
ISBN(电子版)9781538619377
DOI
出版状态已出版 - 2 7月 2017
活动10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2017 - Shanghai, 中国
期限: 14 10月 201716 10月 2017

出版系列

姓名Proceedings - 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2017
2018-January

会议

会议10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2017
国家/地区中国
Shanghai
时期14/10/1716/10/17

指纹

探究 'A dense correspondences matching algorithm with hierarchical pyramid architecture' 的科研主题。它们共同构成独一无二的指纹。

引用此