FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220847702> ?p ?o ?g. }

• W4220847702 endingPage "1164" @default.
• W4220847702 startingPage "1145" @default.
• W4220847702 abstract "We propose a novel convolutional operator for the task of point cloud completion. One striking characteristic of our approach is that, conversely to related work it does not require any max-pooling or voxelization operation. Instead, the proposed operator used to learn the point cloud embedding in the encoder extracts permutation-invariant features from the point cloud via a soft-pooling of feature activations, which are able to preserve fine-grained geometric details. These features are then passed on to a decoder architecture. Due to the compression in the encoder, a typical limitation of this type of architectures is that they tend to lose parts of the input shape structure. We propose to overcome this limitation by using skip connections specifically devised for point clouds, where links between corresponding layers in the encoder and the decoder are established. As part of these connections, we introduce a transformation matrix that projects the features from the encoder to the decoder and vice-versa. The quantitative and qualitative results on the task of object completion from partial scans on the ShapeNet dataset show that incorporating our approach achieves state-of-the-art performance in shape completion both at low and high resolutions." @default.
• W4220847702 created "2022-04-03" @default.
• W4220847702 creator A5041092666 @default.
• W4220847702 creator A5046896448 @default.
• W4220847702 creator A5051298870 @default.
• W4220847702 creator A5079490872 @default.
• W4220847702 date "2022-03-11" @default.
• W4220847702 modified "2023-10-01" @default.
• W4220847702 title "SoftPool++: An Encoder–Decoder Network for Point Cloud Completion" @default.
• W4220847702 cites W1745334888 @default.
• W4220847702 cites W1920022804 @default.
• W4220847702 cites W2132438428 @default.
• W4220847702 cites W2214802144 @default.
• W4220847702 cites W2338532005 @default.
• W4220847702 cites W2342277278 @default.
• W4220847702 cites W2464708700 @default.
• W4220847702 cites W2559882727 @default.
• W4220847702 cites W2776330782 @default.
• W4220847702 cites W2796426482 @default.
• W4220847702 cites W2886499109 @default.
• W4220847702 cites W2888702972 @default.
• W4220847702 cites W2905288042 @default.
• W4220847702 cites W2944579304 @default.
• W4220847702 cites W2953668091 @default.
• W4220847702 cites W2961218591 @default.
• W4220847702 cites W2961368225 @default.
• W4220847702 cites W2963053547 @default.
• W4220847702 cites W2963071695 @default.
• W4220847702 cites W2963264709 @default.
• W4220847702 cites W2963443993 @default.
• W4220847702 cites W2963627347 @default.
• W4220847702 cites W2963735494 @default.
• W4220847702 cites W2968370607 @default.
• W4220847702 cites W2981199548 @default.
• W4220847702 cites W2981604966 @default.
• W4220847702 cites W2981949127 @default.
• W4220847702 cites W2982210492 @default.
• W4220847702 cites W2985683375 @default.
• W4220847702 cites W2987039128 @default.
• W4220847702 cites W2988715931 @default.
• W4220847702 cites W2997088169 @default.
• W4220847702 cites W3025708905 @default.
• W4220847702 cites W3034493208 @default.
• W4220847702 cites W3034584726 @default.
• W4220847702 cites W3034591723 @default.
• W4220847702 cites W3034681945 @default.
• W4220847702 cites W3035014292 @default.
• W4220847702 cites W3035241330 @default.
• W4220847702 cites W3035358681 @default.
• W4220847702 cites W3035398346 @default.
• W4220847702 cites W3035507572 @default.
• W4220847702 cites W3035739565 @default.
• W4220847702 cites W3099201369 @default.
• W4220847702 cites W3105863736 @default.
• W4220847702 cites W3108012830 @default.
• W4220847702 cites W3109518641 @default.
• W4220847702 cites W3116155584 @default.
• W4220847702 cites W3118496930 @default.
• W4220847702 cites W3141954417 @default.
• W4220847702 cites W3170469318 @default.
• W4220847702 cites W3170754649 @default.
• W4220847702 cites W3191573718 @default.
• W4220847702 cites W3192240783 @default.
• W4220847702 cites W3196231425 @default.
• W4220847702 cites W3202611145 @default.
• W4220847702 cites W3203898101 @default.
• W4220847702 cites W3204203737 @default.
• W4220847702 cites W4214505563 @default.
• W4220847702 doi "https://doi.org/10.1007/s11263-022-01588-7" @default.
• W4220847702 hasPublicationYear "2022" @default.
• W4220847702 type Work @default.
• W4220847702 citedByCount "3" @default.
• W4220847702 countsByYear W42208477022023 @default.
• W4220847702 crossrefType "journal-article" @default.
• W4220847702 hasAuthorship W4220847702A5041092666 @default.
• W4220847702 hasAuthorship W4220847702A5046896448 @default.
• W4220847702 hasAuthorship W4220847702A5051298870 @default.
• W4220847702 hasAuthorship W4220847702A5079490872 @default.
• W4220847702 hasBestOaLocation W42208477021 @default.
• W4220847702 hasConcept C111919701 @default.
• W4220847702 hasConcept C11413529 @default.
• W4220847702 hasConcept C118505674 @default.
• W4220847702 hasConcept C121332964 @default.
• W4220847702 hasConcept C131979681 @default.
• W4220847702 hasConcept C154945302 @default.
• W4220847702 hasConcept C190470478 @default.
• W4220847702 hasConcept C21308566 @default.
• W4220847702 hasConcept C24890656 @default.
• W4220847702 hasConcept C2781238097 @default.
• W4220847702 hasConcept C31972630 @default.
• W4220847702 hasConcept C33923547 @default.
• W4220847702 hasConcept C37914503 @default.
• W4220847702 hasConcept C41008148 @default.
• W4220847702 hasConcept C41608201 @default.
• W4220847702 hasConcept C57273362 @default.
• W4220847702 hasConcept C70437156 @default.
• W4220847702 hasConcept C80444323 @default.
• W4220847702 hasConcept C81363708 @default.

• next