HKUST Library Institutional Repository Banner

HKUST Institutional Repository >
Computer Science and Engineering >
CSE Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1783.1/6590
Title: Learning two-view stereo matching
Authors: Xiao, Jianxiong
Chen, Jingni
Yeung, Dit-Yan
Quan Long
Keywords: Dense matching
Stereo matching
Graphics processing unit
Issue Date: Oct-2008
Citation: Proceedings 10th European Conference on Computer Vision, ECCV 2008, Marseille, France, 12-18 October 2008, Part III, LNCS 5304, p. 15-27.
Abstract: We propose a graph-based semi-supervised symmetricmatching framework that performs dense matching between two uncalibrated wide-baseline images by exploiting the results of sparse matching as labeled data. Our method utilizes multiple sources of information including the underlying manifold structure, matching preference, shapes of the surfaces in the scene, and global epipolar geometric constraints for occlusion handling. It can give inherent sub-pixel accuracy and can be implemented in a parallel fashion on a graphics processing unit (GPU). Since the graphs are directly learned from the input images without relying on extra training data, its performance is very stable and hence the method is applicable under general settings. Our algorithm is robust against outliers in the initial sparse matching due to our consideration of all matching costs simultaneously, and the provision of iterative restarts to reject outliers from the previous estimate. Some challenging experiments have been conducted to evaluate the robustness of our method.
Rights: The original publication is available at http://www.springerlink.com/
URI: http://hdl.handle.net/1783.1/6590
Appears in Collections:CSE Conference Papers

Files in This Item:

File Description SizeFormat
matching.pdf3405KbAdobe PDFView/Open

All items in this Repository are protected by copyright, with all rights reserved.