Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225144468> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4225144468 abstract "The non-uniformly distributed nature of the 3D Dynamic Point Cloud (DPC) brings significant challenges to its high-efficient inter-frame compression. This paper proposes a novel 3D sparse convolution-based Deep Dynamic Point Cloud Compression (D-DPCC) network to compensate and compress the DPC geometry with 3D motion estimation and motion compensation in the feature space. In the proposed D-DPCC network, we design a Multi-scale Motion Fusion (MMF) module to accurately estimate the 3D optical flow between the feature representations of adjacent point cloud frames. Specifically, we utilize a 3D sparse convolution-based encoder to obtain the latent representation for motion estimation in the feature space and introduce the proposed MMF module for fused 3D motion embedding. Besides, for motion compensation, we propose a 3D Adaptively Weighted Interpolation (3DAWI) algorithm with a penalty coefficient to adaptively decrease the impact of distant neighbours. We compress the motion embedding and the residual with a lossy autoencoder-based network. To our knowledge, this paper is the first work proposing an end-to-end deep dynamic point cloud compression framework. The experimental result shows that the proposed D-DPCC framework achieves an average 76% BD-Rate (Bjontegaard Delta Rate) gains against state-of-the-art Video-based Point Cloud Compression (V-PCC) v13 in inter mode." @default.
- W4225144468 created "2022-05-01" @default.
- W4225144468 creator A5023991621 @default.
- W4225144468 creator A5038362365 @default.
- W4225144468 creator A5050214771 @default.
- W4225144468 creator A5052676364 @default.
- W4225144468 creator A5056630426 @default.
- W4225144468 creator A5059443966 @default.
- W4225144468 date "2022-07-01" @default.
- W4225144468 modified "2023-09-23" @default.
- W4225144468 title "D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion Prediction" @default.
- W4225144468 doi "https://doi.org/10.24963/ijcai.2022/126" @default.
- W4225144468 hasPublicationYear "2022" @default.
- W4225144468 type Work @default.
- W4225144468 citedByCount "2" @default.
- W4225144468 countsByYear W42251444682022 @default.
- W4225144468 countsByYear W42251444682023 @default.
- W4225144468 crossrefType "proceedings-article" @default.
- W4225144468 hasAuthorship W4225144468A5023991621 @default.
- W4225144468 hasAuthorship W4225144468A5038362365 @default.
- W4225144468 hasAuthorship W4225144468A5050214771 @default.
- W4225144468 hasAuthorship W4225144468A5052676364 @default.
- W4225144468 hasAuthorship W4225144468A5056630426 @default.
- W4225144468 hasAuthorship W4225144468A5059443966 @default.
- W4225144468 hasBestOaLocation W42251444681 @default.
- W4225144468 hasConcept C10161872 @default.
- W4225144468 hasConcept C101738243 @default.
- W4225144468 hasConcept C108583219 @default.
- W4225144468 hasConcept C111919701 @default.
- W4225144468 hasConcept C118505674 @default.
- W4225144468 hasConcept C128840427 @default.
- W4225144468 hasConcept C131979681 @default.
- W4225144468 hasConcept C154945302 @default.
- W4225144468 hasConcept C174493125 @default.
- W4225144468 hasConcept C31972630 @default.
- W4225144468 hasConcept C41008148 @default.
- W4225144468 hasConcept C45347329 @default.
- W4225144468 hasConcept C50644808 @default.
- W4225144468 hasConcept C78548338 @default.
- W4225144468 hasConceptScore W4225144468C10161872 @default.
- W4225144468 hasConceptScore W4225144468C101738243 @default.
- W4225144468 hasConceptScore W4225144468C108583219 @default.
- W4225144468 hasConceptScore W4225144468C111919701 @default.
- W4225144468 hasConceptScore W4225144468C118505674 @default.
- W4225144468 hasConceptScore W4225144468C128840427 @default.
- W4225144468 hasConceptScore W4225144468C131979681 @default.
- W4225144468 hasConceptScore W4225144468C154945302 @default.
- W4225144468 hasConceptScore W4225144468C174493125 @default.
- W4225144468 hasConceptScore W4225144468C31972630 @default.
- W4225144468 hasConceptScore W4225144468C41008148 @default.
- W4225144468 hasConceptScore W4225144468C45347329 @default.
- W4225144468 hasConceptScore W4225144468C50644808 @default.
- W4225144468 hasConceptScore W4225144468C78548338 @default.
- W4225144468 hasLocation W42251444681 @default.
- W4225144468 hasLocation W42251444682 @default.
- W4225144468 hasOpenAccess W4225144468 @default.
- W4225144468 hasPrimaryLocation W42251444681 @default.
- W4225144468 hasRelatedWork W1990455767 @default.
- W4225144468 hasRelatedWork W2028858724 @default.
- W4225144468 hasRelatedWork W2039023179 @default.
- W4225144468 hasRelatedWork W2064234899 @default.
- W4225144468 hasRelatedWork W2132969715 @default.
- W4225144468 hasRelatedWork W2158825824 @default.
- W4225144468 hasRelatedWork W2164116500 @default.
- W4225144468 hasRelatedWork W4206673776 @default.
- W4225144468 hasRelatedWork W578691330 @default.
- W4225144468 hasRelatedWork W851866491 @default.
- W4225144468 isParatext "false" @default.
- W4225144468 isRetracted "false" @default.
- W4225144468 workType "article" @default.