Matches in SemOpenAlex for { <https://semopenalex.org/work/W2922272044> ?p ?o ?g. }
- W2922272044 abstract "We present a deep reinforcement learning method of progressive view inpainting for 3D point scene completion under volume guidance, achieving high-quality scene reconstruction from only a single depth image with severe occlusion. Our approach is end-to-end, consisting of three modules: 3D scene volume reconstruction, 2D depth map inpainting, and multi-view selection for completion. Given a single depth image, our method first 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 depth, and integrating all depth into the point cloud. Since the occluded areas are unavailable, we resort to a deep Q-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 SUNCG data, obtaining better results than the state of the art." @default.
- W2922272044 created "2019-03-22" @default.
- W2922272044 creator A5009164482 @default.
- W2922272044 creator A5017861297 @default.
- W2922272044 creator A5019671036 @default.
- W2922272044 creator A5033153999 @default.
- W2922272044 creator A5042771880 @default.
- W2922272044 creator A5049302033 @default.
- W2922272044 creator A5057649615 @default.
- W2922272044 creator A5058154161 @default.
- W2922272044 creator A5068792201 @default.
- W2922272044 creator A5082819230 @default.
- W2922272044 date "2019-03-10" @default.
- W2922272044 modified "2023-10-16" @default.
- W2922272044 title "Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image" @default.
- W2922272044 cites W1568788419 @default.
- W2922272044 cites W1644641054 @default.
- W2922272044 cites W1927784829 @default.
- W2922272044 cites W1949568868 @default.
- W2922272044 cites W1992642990 @default.
- W2922272044 cites W2000760692 @default.
- W2922272044 cites W2001022596 @default.
- W2922272044 cites W2001140913 @default.
- W2922272044 cites W2014667763 @default.
- W2922272044 cites W2031760064 @default.
- W2922272044 cites W2033483472 @default.
- W2922272044 cites W2049351243 @default.
- W2922272044 cites W2052976238 @default.
- W2922272044 cites W2057316718 @default.
- W2922272044 cites W2060206980 @default.
- W2922272044 cites W2068337491 @default.
- W2922272044 cites W2072202468 @default.
- W2922272044 cites W2077263423 @default.
- W2922272044 cites W2113775403 @default.
- W2922272044 cites W2121669559 @default.
- W2922272044 cites W2132750878 @default.
- W2922272044 cites W2145339207 @default.
- W2922272044 cites W2155968351 @default.
- W2922272044 cites W2174266739 @default.
- W2922272044 cites W2181407706 @default.
- W2922272044 cites W2338532005 @default.
- W2922272044 cites W2342277278 @default.
- W2922272044 cites W2427751284 @default.
- W2922272044 cites W2495603374 @default.
- W2922272044 cites W2520145460 @default.
- W2922272044 cites W2524140598 @default.
- W2922272044 cites W2554344625 @default.
- W2922272044 cites W2557465155 @default.
- W2922272044 cites W2559882727 @default.
- W2922272044 cites W2560722161 @default.
- W2922272044 cites W2612702926 @default.
- W2922272044 cites W2738588019 @default.
- W2922272044 cites W2794739174 @default.
- W2922272044 cites W2797958922 @default.
- W2922272044 cites W2798365772 @default.
- W2922272044 cites W2802805328 @default.
- W2922272044 cites W2807633959 @default.
- W2922272044 cites W2888815532 @default.
- W2922272044 cites W2891464919 @default.
- W2922272044 cites W2913581875 @default.
- W2922272044 cites W2951102653 @default.
- W2922272044 cites W2951799221 @default.
- W2922272044 cites W2962731536 @default.
- W2922272044 cites W2963420272 @default.
- W2922272044 cites W2963648573 @default.
- W2922272044 cites W2964160369 @default.
- W2922272044 cites W305753977 @default.
- W2922272044 cites W3101501663 @default.
- W2922272044 cites W3105308185 @default.
- W2922272044 cites W53941081 @default.
- W2922272044 doi "https://doi.org/10.48550/arxiv.1903.04019" @default.
- W2922272044 hasPublicationYear "2019" @default.
- W2922272044 type Work @default.
- W2922272044 sameAs 2922272044 @default.
- W2922272044 citedByCount "4" @default.
- W2922272044 countsByYear W29222720442020 @default.
- W2922272044 countsByYear W29222720442021 @default.
- W2922272044 crossrefType "posted-content" @default.
- W2922272044 hasAuthorship W2922272044A5009164482 @default.
- W2922272044 hasAuthorship W2922272044A5017861297 @default.
- W2922272044 hasAuthorship W2922272044A5019671036 @default.
- W2922272044 hasAuthorship W2922272044A5033153999 @default.
- W2922272044 hasAuthorship W2922272044A5042771880 @default.
- W2922272044 hasAuthorship W2922272044A5049302033 @default.
- W2922272044 hasAuthorship W2922272044A5057649615 @default.
- W2922272044 hasAuthorship W2922272044A5058154161 @default.
- W2922272044 hasAuthorship W2922272044A5068792201 @default.
- W2922272044 hasAuthorship W2922272044A5082819230 @default.
- W2922272044 hasBestOaLocation W29222720441 @default.
- W2922272044 hasConcept C108583219 @default.
- W2922272044 hasConcept C109950114 @default.
- W2922272044 hasConcept C115961682 @default.
- W2922272044 hasConcept C11727466 @default.
- W2922272044 hasConcept C121332964 @default.
- W2922272044 hasConcept C131979681 @default.
- W2922272044 hasConcept C141268832 @default.
- W2922272044 hasConcept C141379421 @default.
- W2922272044 hasConcept C154945302 @default.
- W2922272044 hasConcept C20556612 @default.
- W2922272044 hasConcept C2524010 @default.