Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296913583> ?p ?o ?g. }
- W4296913583 endingPage "1208" @default.
- W4296913583 startingPage "1198" @default.
- W4296913583 abstract "Motivated by the intuition that the critical step of localizing a 2D image in the corresponding 3D point cloud is establishing 2D-3D correspondence between them, we propose the first feature-based dense correspondence framework for addressing the image-to-point cloud registration problem, dubbed CorrI2P, which consists of three modules, i.e., feature embedding, symmetric overlapping region detection, and pose estimation through the established correspondence. Specifically, given a pair of a 2D image and a 3D point cloud, we first transform them into high-dimensional feature space and feed the resulting features into a symmetric overlapping region detector to determine the region where the image and point cloud overlap each other. Then we use the features of the overlapping regions to establish the 2D-3D correspondence before running EPnP within RANSAC to estimate the camera's pose. Experimental results on KITTI and NuScenes datasets show that our CorrI2P outperforms state-of-the-art image-to-point cloud registration methods significantly. We will make the code publicly available." @default.
- W4296913583 created "2022-09-24" @default.
- W4296913583 creator A5028259707 @default.
- W4296913583 creator A5031957432 @default.
- W4296913583 creator A5072191452 @default.
- W4296913583 creator A5079449734 @default.
- W4296913583 date "2023-03-01" @default.
- W4296913583 modified "2023-10-18" @default.
- W4296913583 title "CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence" @default.
- W4296913583 cites W1875235752 @default.
- W4296913583 cites W1989625560 @default.
- W4296913583 cites W1991544872 @default.
- W4296913583 cites W2002779901 @default.
- W4296913583 cites W2004312117 @default.
- W4296913583 cites W2053580626 @default.
- W4296913583 cites W2083624955 @default.
- W4296913583 cites W2085261163 @default.
- W4296913583 cites W2097832352 @default.
- W4296913583 cites W2115167851 @default.
- W4296913583 cites W2115579991 @default.
- W4296913583 cites W2117228865 @default.
- W4296913583 cites W2124386111 @default.
- W4296913583 cites W2131372145 @default.
- W4296913583 cites W2146881125 @default.
- W4296913583 cites W2149960185 @default.
- W4296913583 cites W2163446794 @default.
- W4296913583 cites W2194775991 @default.
- W4296913583 cites W2200124539 @default.
- W4296913583 cites W2492925340 @default.
- W4296913583 cites W2519911873 @default.
- W4296913583 cites W2560609797 @default.
- W4296913583 cites W2566265240 @default.
- W4296913583 cites W2580440899 @default.
- W4296913583 cites W2584731199 @default.
- W4296913583 cites W2739110650 @default.
- W4296913583 cites W2749379418 @default.
- W4296913583 cites W2789691129 @default.
- W4296913583 cites W2962941647 @default.
- W4296913583 cites W2963264709 @default.
- W4296913583 cites W2963666542 @default.
- W4296913583 cites W2963719584 @default.
- W4296913583 cites W2964014140 @default.
- W4296913583 cites W2968040091 @default.
- W4296913583 cites W2986382673 @default.
- W4296913583 cites W2995435724 @default.
- W4296913583 cites W3013243617 @default.
- W4296913583 cites W3020685487 @default.
- W4296913583 cites W3034675048 @default.
- W4296913583 cites W3035574168 @default.
- W4296913583 cites W3082675008 @default.
- W4296913583 cites W3130129454 @default.
- W4296913583 cites W3134054009 @default.
- W4296913583 cites W3168920280 @default.
- W4296913583 cites W3170994844 @default.
- W4296913583 cites W3176124701 @default.
- W4296913583 cites W3177280664 @default.
- W4296913583 cites W3181308984 @default.
- W4296913583 cites W3185902918 @default.
- W4296913583 doi "https://doi.org/10.1109/tcsvt.2022.3208859" @default.
- W4296913583 hasPublicationYear "2023" @default.
- W4296913583 type Work @default.
- W4296913583 citedByCount "2" @default.
- W4296913583 countsByYear W42969135832023 @default.
- W4296913583 crossrefType "journal-article" @default.
- W4296913583 hasAuthorship W4296913583A5028259707 @default.
- W4296913583 hasAuthorship W4296913583A5031957432 @default.
- W4296913583 hasAuthorship W4296913583A5072191452 @default.
- W4296913583 hasAuthorship W4296913583A5079449734 @default.
- W4296913583 hasBestOaLocation W42969135832 @default.
- W4296913583 hasConcept C111919701 @default.
- W4296913583 hasConcept C114744707 @default.
- W4296913583 hasConcept C115961682 @default.
- W4296913583 hasConcept C131979681 @default.
- W4296913583 hasConcept C138885662 @default.
- W4296913583 hasConcept C153180895 @default.
- W4296913583 hasConcept C154945302 @default.
- W4296913583 hasConcept C166704113 @default.
- W4296913583 hasConcept C179458375 @default.
- W4296913583 hasConcept C2524010 @default.
- W4296913583 hasConcept C2776401178 @default.
- W4296913583 hasConcept C28719098 @default.
- W4296913583 hasConcept C31972630 @default.
- W4296913583 hasConcept C33923547 @default.
- W4296913583 hasConcept C41008148 @default.
- W4296913583 hasConcept C41608201 @default.
- W4296913583 hasConcept C41895202 @default.
- W4296913583 hasConcept C52102323 @default.
- W4296913583 hasConcept C79974875 @default.
- W4296913583 hasConceptScore W4296913583C111919701 @default.
- W4296913583 hasConceptScore W4296913583C114744707 @default.
- W4296913583 hasConceptScore W4296913583C115961682 @default.
- W4296913583 hasConceptScore W4296913583C131979681 @default.
- W4296913583 hasConceptScore W4296913583C138885662 @default.
- W4296913583 hasConceptScore W4296913583C153180895 @default.
- W4296913583 hasConceptScore W4296913583C154945302 @default.
- W4296913583 hasConceptScore W4296913583C166704113 @default.
- W4296913583 hasConceptScore W4296913583C179458375 @default.
- W4296913583 hasConceptScore W4296913583C2524010 @default.