This paper deals with deep neural networks for predicting accurate dense disparity map with Semi-global matching (SGM). SGM is a widely used regularization method for real scenes because of its high accuracy and fast computation speed. Even though SGM can obtain accurate results, tuning of SGMs penalty-parameters, which control a smoothness and discontinuity of a disparity map, is uneasy and empirical methods have been proposed. We propose a learning based penalties estimation method, which we call SGM-Nets that consist of Convolutional Neural Networks. A small image patch and its position are input into SGMNets to predict the penalties for the 3D object structures. In order to train the networks, we introduce a novel loss function which is able to use sparsely annotated disparity maps such as captured by a LiDAR sensor in real environments. Moreover, we propose a novel SGM parameterization, which deploys different penalties depending on either positive or negative disparity changes in order to represent the object structures more discriminatively. Our SGM-Nets outperformed state of the art accuracy on KITTI benchmark datasets.<\/p>\n","protected":false},"excerpt":{"rendered":"
This paper deals with deep neural networks for predicting accurate dense disparity map with Semi-global matching (SGM). SGM is a widely used regularization method for real scenes because of its high accuracy and fast computation speed. Even though SGM can obtain accurate results, tuning of SGMs penalty-parameters, which control a smoothness and discontinuity of a […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13562],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-610017","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-computer-vision","msr-locale-en_us"],"msr_publishername":"IEEE","msr_edition":"","msr_affiliation":"","msr_published_date":"2017-7","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"IEEE\/CVF","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2019\/09\/Seki_SGM-Nets_Semi-Global_Matching_CVPR_2017_paper.pdf","id":"610020","title":"seki_sgm-nets_semi-global_matching_cvpr_2017_paper","label_id":"243132","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/ieeexplore.ieee.org\/document\/8100186","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":610020,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2019\/09\/Seki_SGM-Nets_Semi-Global_Matching_CVPR_2017_paper.pdf"}],"msr-author-ordering":[{"type":"text","value":"Akihito Seki","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Marc Pollefeys","user_id":36191,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Marc Pollefeys"}],"msr_impact_theme":[],"msr_research_lab":[602418],"msr_event":[397277],"msr_group":[],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/610017"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/610017\/revisions"}],"predecessor-version":[{"id":610023,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/610017\/revisions\/610023"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=610017"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=610017"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=610017"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=610017"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=610017"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=610017"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=610017"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=610017"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=610017"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=610017"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=610017"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=610017"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=610017"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=610017"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=610017"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}