Computing the Stereo Matching Cost with a Convolutional Neural Network Seminar Recent Trends in 3D Computer Vision. Herb, M. Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on, 2015.
![Computing the Stereo Matching Cost with a Convolutional Neural Network Seminar Recent Trends in 3D Computer Vision [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex
Paper abstract bibtex We present a method for extracting depth information from a rectified image pair. We train a convolutional neu- ral 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 elim- inate 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
@article{
title = {Computing the Stereo Matching Cost with a Convolutional Neural Network Seminar Recent Trends in 3D Computer Vision},
type = {article},
year = {2015},
pages = {1592-1599},
id = {eb0b8dce-e48b-3bcb-abae-f9519618d0a5},
created = {2022-09-19T09:01:26.166Z},
file_attached = {true},
profile_id = {276016a7-2c9d-3507-8888-093db7c54774},
group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},
last_modified = {2022-09-19T09:03:13.876Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
folder_uuids = {02fb5526-03ff-44ad-8d5c-42bd496c3100},
private_publication = {false},
abstract = {We present a method for extracting depth information from a rectified image pair. We train a convolutional neu- ral 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 elim- inate 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},
bibtype = {article},
author = {Herb, Markus},
journal = {Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on},
number = {1}
}Downloads: 0
{"_id":"oiiWWdNNPMY5iqgfS","bibbaseid":"herb-computingthestereomatchingcostwithaconvolutionalneuralnetworkseminarrecenttrendsin3dcomputervision-2015","author_short":["Herb, M."],"bibdata":{"title":"Computing the Stereo Matching Cost with a Convolutional Neural Network Seminar Recent Trends in 3D Computer Vision","type":"article","year":"2015","pages":"1592-1599","id":"eb0b8dce-e48b-3bcb-abae-f9519618d0a5","created":"2022-09-19T09:01:26.166Z","file_attached":"true","profile_id":"276016a7-2c9d-3507-8888-093db7c54774","group_id":"5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1","last_modified":"2022-09-19T09:03:13.876Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"folder_uuids":"02fb5526-03ff-44ad-8d5c-42bd496c3100","private_publication":false,"abstract":"We present a method for extracting depth information from a rectified image pair. We train a convolutional neu- ral 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 elim- inate 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","bibtype":"article","author":"Herb, Markus","journal":"Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on","number":"1","bibtex":"@article{\n title = {Computing the Stereo Matching Cost with a Convolutional Neural Network Seminar Recent Trends in 3D Computer Vision},\n type = {article},\n year = {2015},\n pages = {1592-1599},\n id = {eb0b8dce-e48b-3bcb-abae-f9519618d0a5},\n created = {2022-09-19T09:01:26.166Z},\n file_attached = {true},\n profile_id = {276016a7-2c9d-3507-8888-093db7c54774},\n group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},\n last_modified = {2022-09-19T09:03:13.876Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n folder_uuids = {02fb5526-03ff-44ad-8d5c-42bd496c3100},\n private_publication = {false},\n abstract = {We present a method for extracting depth information from a rectified image pair. We train a convolutional neu- ral 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 elim- inate 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},\n bibtype = {article},\n author = {Herb, Markus},\n journal = {Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on},\n number = {1}\n}","author_short":["Herb, M."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/67f075bd-2b90-6283-0dcf-b047e4088d0e/zbontar2015.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"herb-computingthestereomatchingcostwithaconvolutionalneuralnetworkseminarrecenttrendsin3dcomputervision-2015","role":"author","metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["2252seNhipfTmjEBQ"],"keywords":[],"search_terms":["computing","stereo","matching","cost","convolutional","neural","network","seminar","recent","trends","computer","vision","herb"],"title":"Computing the Stereo Matching Cost with a Convolutional Neural Network Seminar Recent Trends in 3D Computer Vision","year":2015}