Matches in SemOpenAlex for { <https://semopenalex.org/work/W2798881637> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2798881637 abstract "Cross-spectral imaging provides strong benefits for recognition and detection tasks. Often, multiple cameras are used for cross-spectral imaging, thus requiring image alignment, or disparity estimation in a stereo setting. Increasingly, multi-camera cross-spectral systems are embedded in active RGBD devices (e.g. RGB-NIR cameras in Kinect and iPhone X). Hence, stereo matching also provides an opportunity to obtain depth without an active projector source. However, matching images from different spectral bands is challenging because of large appearance variations. We develop a novel deep learning framework to simultaneously transform images across spectral bands and estimate disparity. A material-aware loss function is incorporated within the disparity prediction network to handle regions with unreliable matching such as light sources, glass windshields and glossy surfaces. No depth supervision is required by our method. To evaluate our method, we used a vehicle-mounted RGB-NIR stereo system to collect 13.7 hours of video data across a range of areas in and around a city. Experiments show that our method achieves strong performance and reaches real-time speed." @default.
- W2798881637 created "2018-05-07" @default.
- W2798881637 creator A5029497982 @default.
- W2798881637 creator A5049902435 @default.
- W2798881637 creator A5075246991 @default.
- W2798881637 creator A5080638933 @default.
- W2798881637 date "2018-06-01" @default.
- W2798881637 modified "2023-10-09" @default.
- W2798881637 title "Deep Material-Aware Cross-Spectral Stereo Matching" @default.
- W2798881637 cites W1910108985 @default.
- W2798881637 cites W1940079326 @default.
- W2798881637 cites W2012893378 @default.
- W2798881637 cites W2017626840 @default.
- W2798881637 cites W2031489346 @default.
- W2798881637 cites W2033687086 @default.
- W2798881637 cites W2062415280 @default.
- W2798881637 cites W2108598243 @default.
- W2798881637 cites W2125656989 @default.
- W2798881637 cites W2133665775 @default.
- W2798881637 cites W2159579259 @default.
- W2798881637 cites W2161969291 @default.
- W2798881637 cites W2163309385 @default.
- W2798881637 cites W2341900193 @default.
- W2798881637 cites W2402505869 @default.
- W2798881637 cites W2462140767 @default.
- W2798881637 cites W2520707372 @default.
- W2798881637 cites W2551624499 @default.
- W2798881637 cites W2593414960 @default.
- W2798881637 cites W2608295741 @default.
- W2798881637 cites W2609883120 @default.
- W2798881637 cites W2776033207 @default.
- W2798881637 cites W2779124836 @default.
- W2798881637 cites W2789934631 @default.
- W2798881637 doi "https://doi.org/10.1109/cvpr.2018.00205" @default.
- W2798881637 hasPublicationYear "2018" @default.
- W2798881637 type Work @default.
- W2798881637 sameAs 2798881637 @default.
- W2798881637 citedByCount "31" @default.
- W2798881637 countsByYear W27988816372019 @default.
- W2798881637 countsByYear W27988816372020 @default.
- W2798881637 countsByYear W27988816372021 @default.
- W2798881637 countsByYear W27988816372022 @default.
- W2798881637 countsByYear W27988816372023 @default.
- W2798881637 crossrefType "proceedings-article" @default.
- W2798881637 hasAuthorship W2798881637A5029497982 @default.
- W2798881637 hasAuthorship W2798881637A5049902435 @default.
- W2798881637 hasAuthorship W2798881637A5075246991 @default.
- W2798881637 hasAuthorship W2798881637A5080638933 @default.
- W2798881637 hasConcept C105795698 @default.
- W2798881637 hasConcept C154945302 @default.
- W2798881637 hasConcept C165064840 @default.
- W2798881637 hasConcept C205649164 @default.
- W2798881637 hasConcept C2776122016 @default.
- W2798881637 hasConcept C2776865275 @default.
- W2798881637 hasConcept C31972630 @default.
- W2798881637 hasConcept C3232514 @default.
- W2798881637 hasConcept C33923547 @default.
- W2798881637 hasConcept C41008148 @default.
- W2798881637 hasConcept C62649853 @default.
- W2798881637 hasConcept C82990744 @default.
- W2798881637 hasConceptScore W2798881637C105795698 @default.
- W2798881637 hasConceptScore W2798881637C154945302 @default.
- W2798881637 hasConceptScore W2798881637C165064840 @default.
- W2798881637 hasConceptScore W2798881637C205649164 @default.
- W2798881637 hasConceptScore W2798881637C2776122016 @default.
- W2798881637 hasConceptScore W2798881637C2776865275 @default.
- W2798881637 hasConceptScore W2798881637C31972630 @default.
- W2798881637 hasConceptScore W2798881637C3232514 @default.
- W2798881637 hasConceptScore W2798881637C33923547 @default.
- W2798881637 hasConceptScore W2798881637C41008148 @default.
- W2798881637 hasConceptScore W2798881637C62649853 @default.
- W2798881637 hasConceptScore W2798881637C82990744 @default.
- W2798881637 hasLocation W27988816371 @default.
- W2798881637 hasOpenAccess W2798881637 @default.
- W2798881637 hasPrimaryLocation W27988816371 @default.
- W2798881637 hasRelatedWork W2004755571 @default.
- W2798881637 hasRelatedWork W2052518016 @default.
- W2798881637 hasRelatedWork W2081022503 @default.
- W2798881637 hasRelatedWork W2085956791 @default.
- W2798881637 hasRelatedWork W2283162247 @default.
- W2798881637 hasRelatedWork W2314488738 @default.
- W2798881637 hasRelatedWork W2524507886 @default.
- W2798881637 hasRelatedWork W2771653066 @default.
- W2798881637 hasRelatedWork W2901949253 @default.
- W2798881637 hasRelatedWork W4212983513 @default.
- W2798881637 isParatext "false" @default.
- W2798881637 isRetracted "false" @default.
- W2798881637 magId "2798881637" @default.
- W2798881637 workType "article" @default.