Please use this identifier to cite or link to this item:

Learning Two-View Stereo Matching

Authors Xiao,Jianxiong HKUST affiliated (currently or previously)
Yeung,Dit-Yan View this author's profile
Quan,Long View this author's profile
Issue Date 2008
Source 10th European Conference on Computer Vision (ECCV 2008), Marseille (France) , 12-18 Oct 2008, p. 15-27.
Summary 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
Language English
Format Conference paper
Files in this item:
File Description Size Format
matching.pdf 3486721 B Adobe PDF