FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3217381013> ?p ?o ?g. }

• W3217381013 abstract "Point cloud obtained from 3D scanning is often sparse, noisy, and irregular. To cope with these issues, recent studies have been separately conducted to densify, denoise, and complete inaccurate point cloud. In this paper, we advocate that jointly solving these tasks leads to significant improvement for point cloud reconstruction. To this end, we propose a deep point cloud reconstruction network consisting of two stages: 1) a 3D sparse stacked-hourglass network as for the initial densification and denoising, 2) a refinement via transformers converting the discrete voxels into 3D points. In particular, we further improve the performance of transformer by a newly proposed module called amplified positional encoding. This module has been designed to differently amplify the magnitude of positional encoding vectors based on the points' distances for adaptive refinements. Extensive experiments demonstrate that our network achieves state-of-the-art performance among the recent studies in the ScanNet, ICL-NUIM, and ShapeNetPart datasets. Moreover, we underline the ability of our network to generalize toward real-world and unmet scenes." @default.
• W3217381013 created "2021-12-06" @default.
• W3217381013 creator A5005961868 @default.
• W3217381013 creator A5012455275 @default.
• W3217381013 creator A5062449260 @default.
• W3217381013 creator A5079204970 @default.
• W3217381013 creator A5090418377 @default.
• W3217381013 date "2021-11-23" @default.
• W3217381013 modified "2023-09-27" @default.
• W3217381013 title "Deep Point Cloud Reconstruction" @default.
• W3217381013 cites W1522301498 @default.
• W3217381013 cites W1974102081 @default.
• W3217381013 cites W1986234613 @default.
• W3217381013 cites W1987113397 @default.
• W3217381013 cites W2008073424 @default.
• W3217381013 cites W2009422376 @default.
• W3217381013 cites W2021369132 @default.
• W3217381013 cites W2058535340 @default.
• W3217381013 cites W2078290150 @default.
• W3217381013 cites W2100816864 @default.
• W3217381013 cites W2121535648 @default.
• W3217381013 cites W2123732640 @default.
• W3217381013 cites W2124246957 @default.
• W3217381013 cites W2137531922 @default.
• W3217381013 cites W2169611956 @default.
• W3217381013 cites W2171094068 @default.
• W3217381013 cites W2190691619 @default.
• W3217381013 cites W2229412420 @default.
• W3217381013 cites W2249773824 @default.
• W3217381013 cites W2307770531 @default.
• W3217381013 cites W2338968644 @default.
• W3217381013 cites W2366389387 @default.
• W3217381013 cites W2553307952 @default.
• W3217381013 cites W2560722161 @default.
• W3217381013 cites W2594519801 @default.
• W3217381013 cites W2624273542 @default.
• W3217381013 cites W2738551266 @default.
• W3217381013 cites W2786036844 @default.
• W3217381013 cites W2798965597 @default.
• W3217381013 cites W2805499196 @default.
• W3217381013 cites W2886499109 @default.
• W3217381013 cites W2897097528 @default.
• W3217381013 cites W2906788812 @default.
• W3217381013 cites W2909918887 @default.
• W3217381013 cites W2940235493 @default.
• W3217381013 cites W2950493473 @default.
• W3217381013 cites W2962793285 @default.
• W3217381013 cites W2962818872 @default.
• W3217381013 cites W2963125977 @default.
• W3217381013 cites W2963177347 @default.
• W3217381013 cites W2963390820 @default.
• W3217381013 cites W2963403868 @default.
• W3217381013 cites W2963619659 @default.
• W3217381013 cites W2963627347 @default.
• W3217381013 cites W2963680153 @default.
• W3217381013 cites W2963860281 @default.
• W3217381013 cites W2964062501 @default.
• W3217381013 cites W2968296999 @default.
• W3217381013 cites W2982210492 @default.
• W3217381013 cites W2996166203 @default.
• W3217381013 cites W3011537551 @default.
• W3217381013 cites W3034314779 @default.
• W3217381013 cites W3034584726 @default.
• W3217381013 cites W3034986117 @default.
• W3217381013 cites W3035030518 @default.
• W3217381013 cites W3039448353 @default.
• W3217381013 cites W3092203888 @default.
• W3217381013 cites W3096387236 @default.
• W3217381013 cites W3106779726 @default.
• W3217381013 cites W3108012830 @default.
• W3217381013 cites W3112996878 @default.
• W3217381013 cites W3145086533 @default.
• W3217381013 cites W3170469318 @default.
• W3217381013 cites W3170953222 @default.
• W3217381013 cites W3175676582 @default.
• W3217381013 cites W3179923621 @default.
• W3217381013 cites W3191573718 @default.
• W3217381013 cites W3202828730 @default.
• W3217381013 doi "https://doi.org/10.48550/arxiv.2111.11704" @default.
• W3217381013 hasPublicationYear "2021" @default.
• W3217381013 type Work @default.
• W3217381013 sameAs 3217381013 @default.
• W3217381013 citedByCount "1" @default.
• W3217381013 countsByYear W32173810132021 @default.
• W3217381013 crossrefType "posted-content" @default.
• W3217381013 hasAuthorship W3217381013A5005961868 @default.
• W3217381013 hasAuthorship W3217381013A5012455275 @default.
• W3217381013 hasAuthorship W3217381013A5062449260 @default.
• W3217381013 hasAuthorship W3217381013A5079204970 @default.
• W3217381013 hasAuthorship W3217381013A5090418377 @default.
• W3217381013 hasBestOaLocation W32173810131 @default.
• W3217381013 hasConcept C111919701 @default.
• W3217381013 hasConcept C11413529 @default.
• W3217381013 hasConcept C124101348 @default.
• W3217381013 hasConcept C125411270 @default.
• W3217381013 hasConcept C131979681 @default.
• W3217381013 hasConcept C154945302 @default.
• W3217381013 hasConcept C163294075 @default.
• W3217381013 hasConcept C2524010 @default.
• W3217381013 hasConcept C28719098 @default.

• next