Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362601944> ?p ?o ?g. }
- W4362601944 endingPage "11095" @default.
- W4362601944 startingPage "11079" @default.
- W4362601944 abstract "We present a deep reinforcement learning method of progressive view inpainting for colored semantic point cloud scene completion under volume guidance, achieving high-quality scene reconstruction from only a single RGB-D image with severe occlusion. Our approach is end-to-end, consisting of three modules: 3D scene volume reconstruction, 2D RGB-D and segmentation image inpainting, and multi-view selection for completion. Given a single RGB-D image, our method first predicts its semantic segmentation map and goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide to the next view inpainting step, which attempts to make up the missing information; the third step involves projecting the volume under the same view of the input, concatenating them to complete the current view RGB-D and segmentation map, and integrating all RGB-D and segmentation maps into the point cloud. Since the occluded areas are unavailable, we resort to a A3C network to glance around and pick the next best view for large hole completion progressively until a scene is adequately reconstructed while guaranteeing validity. All steps are learned jointly to achieve robust and consistent results. We perform qualitative and quantitative evaluations with extensive experiments on the 3D-FUTURE data, obtaining better results than state-of-the-arts." @default.
- W4362601944 created "2023-04-06" @default.
- W4362601944 creator A5020527092 @default.
- W4362601944 creator A5024718359 @default.
- W4362601944 creator A5026053703 @default.
- W4362601944 creator A5069242888 @default.
- W4362601944 creator A5072072030 @default.
- W4362601944 creator A5075757992 @default.
- W4362601944 date "2023-09-01" @default.
- W4362601944 modified "2023-10-15" @default.
- W4362601944 title "Point Cloud Scene Completion With Joint Color and Semantic Estimation From Single RGB-D Image" @default.
- W4362601944 cites W1644641054 @default.
- W4362601944 cites W1927784829 @default.
- W4362601944 cites W1949568868 @default.
- W4362601944 cites W1981349497 @default.
- W4362601944 cites W1992642990 @default.
- W4362601944 cites W2000760692 @default.
- W4362601944 cites W2001022596 @default.
- W4362601944 cites W2001140913 @default.
- W4362601944 cites W2012788443 @default.
- W4362601944 cites W2014667763 @default.
- W4362601944 cites W2031760064 @default.
- W4362601944 cites W2033483472 @default.
- W4362601944 cites W2049351243 @default.
- W4362601944 cites W2057316718 @default.
- W4362601944 cites W2060206980 @default.
- W4362601944 cites W2061987443 @default.
- W4362601944 cites W2068337491 @default.
- W4362601944 cites W2072202468 @default.
- W4362601944 cites W2077263423 @default.
- W4362601944 cites W2113775403 @default.
- W4362601944 cites W2121669559 @default.
- W4362601944 cites W2132750878 @default.
- W4362601944 cites W2145339207 @default.
- W4362601944 cites W2338532005 @default.
- W4362601944 cites W2342277278 @default.
- W4362601944 cites W2495603374 @default.
- W4362601944 cites W2520145460 @default.
- W4362601944 cites W2524140598 @default.
- W4362601944 cites W2554344625 @default.
- W4362601944 cites W2557465155 @default.
- W4362601944 cites W2559882727 @default.
- W4362601944 cites W2560722161 @default.
- W4362601944 cites W2594519801 @default.
- W4362601944 cites W2609719703 @default.
- W4362601944 cites W2612702926 @default.
- W4362601944 cites W2738588019 @default.
- W4362601944 cites W2746553466 @default.
- W4362601944 cites W2794739174 @default.
- W4362601944 cites W2796426482 @default.
- W4362601944 cites W2798365772 @default.
- W4362601944 cites W2886499109 @default.
- W4362601944 cites W2888815532 @default.
- W4362601944 cites W2940600945 @default.
- W4362601944 cites W2955058313 @default.
- W4362601944 cites W2962697464 @default.
- W4362601944 cites W2962731536 @default.
- W4362601944 cites W2962774226 @default.
- W4362601944 cites W2962793285 @default.
- W4362601944 cites W2963420272 @default.
- W4362601944 cites W2963640720 @default.
- W4362601944 cites W2963648573 @default.
- W4362601944 cites W2963708502 @default.
- W4362601944 cites W2963739349 @default.
- W4362601944 cites W2964160369 @default.
- W4362601944 cites W2964266557 @default.
- W4362601944 cites W2977090839 @default.
- W4362601944 cites W2981199548 @default.
- W4362601944 cites W2981604966 @default.
- W4362601944 cites W2981682056 @default.
- W4362601944 cites W2991084087 @default.
- W4362601944 cites W3014538210 @default.
- W4362601944 cites W3034528136 @default.
- W4362601944 cites W3034584726 @default.
- W4362601944 cites W3034868495 @default.
- W4362601944 cites W3035308182 @default.
- W4362601944 cites W3035426499 @default.
- W4362601944 cites W3035512475 @default.
- W4362601944 cites W3101501663 @default.
- W4362601944 cites W3103830808 @default.
- W4362601944 cites W3105308185 @default.
- W4362601944 cites W4252405433 @default.
- W4362601944 cites W4308769670 @default.
- W4362601944 cites W4312796067 @default.
- W4362601944 cites W53941081 @default.
- W4362601944 doi "https://doi.org/10.1109/tpami.2023.3264449" @default.
- W4362601944 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37018106" @default.
- W4362601944 hasPublicationYear "2023" @default.
- W4362601944 type Work @default.
- W4362601944 citedByCount "0" @default.
- W4362601944 crossrefType "journal-article" @default.
- W4362601944 hasAuthorship W4362601944A5020527092 @default.
- W4362601944 hasAuthorship W4362601944A5024718359 @default.
- W4362601944 hasAuthorship W4362601944A5026053703 @default.
- W4362601944 hasAuthorship W4362601944A5069242888 @default.
- W4362601944 hasAuthorship W4362601944A5072072030 @default.
- W4362601944 hasAuthorship W4362601944A5075757992 @default.
- W4362601944 hasBestOaLocation W43626019442 @default.