Computing the Stereo Matching Cost with a Convolutional Neural Network
CVPR(2015)
摘要
We present a method for extracting depth information from a rectified image pair. We train a convolutional neural network to predict how well two image patches match and use it to compute the stereo matching cost. The cost is refined by cross-based cost aggregation and semiglobal matching, followed by a left-right consistency check to eliminate errors in the occluded regions. Our stereo method achieves an error rate of 2.61 % on the KITTI stereo dataset and is currently (August 2014) the top performing method on this dataset.
更多查看译文
关键词
stereo matching cost,depth information extraction,rectified image pair,convolutional neural network training,image patch matching,cross-based cost aggregation,semiglobal matching,left-right consistency check,KITTI stereo dataset
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要