FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210235006> ?p ?o ?g. }

• W3210235006 abstract "3D hand reconstruction is a popular research topic in recent years, which has great potential for VR/AR applications. However, due to the limited computational resource of VR/AR equipment, the reconstruction algorithm must balance accuracy and efficiency to make the users have a good experience. Nevertheless, current methods are not doing well in balancing accuracy and efficiency. Therefore, this paper proposes a novel framework that can achieve a fast and accurate 3D hand reconstruction. Our framework relies on three essential modules, including spatial-aware initial graph building (SAIGB), graph convolutional network (GCN) based belief maps regression (GBBMR), and pose-guided refinement (PGR). At first, given image feature maps extracted by convolutional neural networks, SAIGB builds a spatial-aware and compact initial feature graph. Each node in this graph represents a vertex of the mesh and has vertex-specific spatial information that is helpful for accurate and efficient regression. After that, GBBMR first utilizes adaptive-GCN to introduce interactions between vertices to capture short-range and long-range dependencies between vertices efficiently and flexibly. Then, it maps vertices’ features to belief maps that can model the uncertainty of predictions for more accurate predictions. Finally, we apply PGR to compress the redundant vertices’ belief maps to compact-joints’ belief maps with the pose guidance and use these joints’ belief maps to refine previous predictions better to obtain more accurate and robust reconstruction results. Our method achieves state-of-the-art performance on four public benchmarks, FreiHAND, HO-3D, RHD, and STB. Moreover, our method can run at a speed of two to three times that of previous state-of-the-art methods. Our code is available at https://github.com/zxz267/SAR." @default.
• W3210235006 created "2021-11-08" @default.
• W3210235006 creator A5008194128 @default.
• W3210235006 creator A5055561636 @default.
• W3210235006 creator A5055685073 @default.
• W3210235006 creator A5058120492 @default.
• W3210235006 creator A5071363803 @default.
• W3210235006 creator A5080553004 @default.
• W3210235006 date "2021-10-01" @default.
• W3210235006 modified "2023-09-26" @default.
• W3210235006 title "SAR: Spatial-Aware Regression for 3D Hand Pose and Mesh Reconstruction from a Monocular RGB Image" @default.
• W3210235006 cites W1987648924 @default.
• W3210235006 cites W2108598243 @default.
• W3210235006 cites W2112796928 @default.
• W3210235006 cites W2194775991 @default.
• W3210235006 cites W2768683308 @default.
• W3210235006 cites W2892644985 @default.
• W3210235006 cites W2909817422 @default.
• W3210235006 cites W2943102817 @default.
• W3210235006 cites W2962778872 @default.
• W3210235006 cites W2962811204 @default.
• W3210235006 cites W2963207848 @default.
• W3210235006 cites W2963907666 @default.
• W3210235006 cites W2964093990 @default.
• W3210235006 cites W2968722025 @default.
• W3210235006 cites W2973857456 @default.
• W3210235006 cites W2979577579 @default.
• W3210235006 cites W2981920153 @default.
• W3210235006 cites W2982601397 @default.
• W3210235006 cites W2984612350 @default.
• W3210235006 cites W2984624776 @default.
• W3210235006 cites W2998273692 @default.
• W3210235006 cites W3000368443 @default.
• W3210235006 cites W3000511201 @default.
• W3210235006 cites W3009850394 @default.
• W3210235006 cites W3014641072 @default.
• W3210235006 cites W3021322563 @default.
• W3210235006 cites W3034470433 @default.
• W3210235006 cites W3034479523 @default.
• W3210235006 cites W3035385851 @default.
• W3210235006 cites W3036625283 @default.
• W3210235006 cites W3107620906 @default.
• W3210235006 cites W3109877674 @default.
• W3210235006 cites W3112291480 @default.
• W3210235006 cites W3113017205 @default.
• W3210235006 cites W3121324303 @default.
• W3210235006 doi "https://doi.org/10.1109/ismar52148.2021.00024" @default.
• W3210235006 hasPublicationYear "2021" @default.
• W3210235006 type Work @default.
• W3210235006 sameAs 3210235006 @default.
• W3210235006 citedByCount "2" @default.
• W3210235006 countsByYear W32102350062023 @default.
• W3210235006 crossrefType "proceedings-article" @default.
• W3210235006 hasAuthorship W3210235006A5008194128 @default.
• W3210235006 hasAuthorship W3210235006A5055561636 @default.
• W3210235006 hasAuthorship W3210235006A5055685073 @default.
• W3210235006 hasAuthorship W3210235006A5058120492 @default.
• W3210235006 hasAuthorship W3210235006A5071363803 @default.
• W3210235006 hasAuthorship W3210235006A5080553004 @default.
• W3210235006 hasConcept C105795698 @default.
• W3210235006 hasConcept C11413529 @default.
• W3210235006 hasConcept C132525143 @default.
• W3210235006 hasConcept C138885662 @default.
• W3210235006 hasConcept C153180895 @default.
• W3210235006 hasConcept C154945302 @default.
• W3210235006 hasConcept C159985019 @default.
• W3210235006 hasConcept C192562407 @default.
• W3210235006 hasConcept C204323151 @default.
• W3210235006 hasConcept C2776401178 @default.
• W3210235006 hasConcept C33923547 @default.
• W3210235006 hasConcept C41008148 @default.
• W3210235006 hasConcept C41895202 @default.
• W3210235006 hasConcept C65909025 @default.
• W3210235006 hasConcept C80444323 @default.
• W3210235006 hasConcept C80899671 @default.
• W3210235006 hasConcept C81363708 @default.
• W3210235006 hasConcept C82990744 @default.
• W3210235006 hasConcept C83546350 @default.
• W3210235006 hasConceptScore W3210235006C105795698 @default.
• W3210235006 hasConceptScore W3210235006C11413529 @default.
• W3210235006 hasConceptScore W3210235006C132525143 @default.
• W3210235006 hasConceptScore W3210235006C138885662 @default.
• W3210235006 hasConceptScore W3210235006C153180895 @default.
• W3210235006 hasConceptScore W3210235006C154945302 @default.
• W3210235006 hasConceptScore W3210235006C159985019 @default.
• W3210235006 hasConceptScore W3210235006C192562407 @default.
• W3210235006 hasConceptScore W3210235006C204323151 @default.
• W3210235006 hasConceptScore W3210235006C2776401178 @default.
• W3210235006 hasConceptScore W3210235006C33923547 @default.
• W3210235006 hasConceptScore W3210235006C41008148 @default.
• W3210235006 hasConceptScore W3210235006C41895202 @default.
• W3210235006 hasConceptScore W3210235006C65909025 @default.
• W3210235006 hasConceptScore W3210235006C80444323 @default.
• W3210235006 hasConceptScore W3210235006C80899671 @default.
• W3210235006 hasConceptScore W3210235006C81363708 @default.
• W3210235006 hasConceptScore W3210235006C82990744 @default.
• W3210235006 hasConceptScore W3210235006C83546350 @default.
• W3210235006 hasFunder F4320321001 @default.
• W3210235006 hasFunder F4320321408 @default.
• W3210235006 hasFunder F4320321543 @default.

• next