Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092349220> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3092349220 abstract "We consider the task of predicting 3D object shapes from color images on mobile platforms, which has many real-world applications including augmented reality (AR), virtual reality (VR), and robotics. Recent work has developed a Graph Convolution Network (GCN) based approach to produce 3D object shapes in the form of a triangular mesh of increasing polycount (no. of triangles in the mesh). In this paper, we propose a novel approach to trade-off polycount of a 3D object shape for the energy consumed at run-time called Polycount-Energy Trade-off networks (PETNet). The key idea behind PETNets is to design an architecture of increasing complexity with a comparator module and leveraging the pre-trained GCN to perform input-specific adaptive predictions. We perform experiments using pre-trained GCN on the ShapeNet dataset. Results show that with the optimized PETNets, we can get up to 20%-37% gain in energy for negligible loss (0.01 to 0.02) in accuracy, and provides a fine-grained control on performance when compared to a fixed level performance with the state-of-the-art Pixel2Mesh network." @default.
- W3092349220 created "2020-10-15" @default.
- W3092349220 creator A5055445718 @default.
- W3092349220 creator A5078441163 @default.
- W3092349220 creator A5083092166 @default.
- W3092349220 date "2020-07-01" @default.
- W3092349220 modified "2023-09-23" @default.
- W3092349220 title "PETNet: Polycount and Energy Trade-off Deep Networks for Producing 3D Objects from Images" @default.
- W3092349220 cites W2048266589 @default.
- W3092349220 cites W2116341502 @default.
- W3092349220 cites W2190691619 @default.
- W3092349220 cites W2194775991 @default.
- W3092349220 cites W2267244539 @default.
- W3092349220 cites W2285660444 @default.
- W3092349220 cites W2342277278 @default.
- W3092349220 cites W2516141709 @default.
- W3092349220 cites W2523838129 @default.
- W3092349220 cites W2554302513 @default.
- W3092349220 cites W2560722161 @default.
- W3092349220 cites W2604319603 @default.
- W3092349220 cites W2605347906 @default.
- W3092349220 cites W2612445135 @default.
- W3092349220 cites W2626712922 @default.
- W3092349220 cites W2791845808 @default.
- W3092349220 cites W2895298874 @default.
- W3092349220 cites W2962778872 @default.
- W3092349220 cites W2962835968 @default.
- W3092349220 cites W2963527086 @default.
- W3092349220 cites W2963563548 @default.
- W3092349220 cites W2963674932 @default.
- W3092349220 cites W2964015378 @default.
- W3092349220 cites W2964578286 @default.
- W3092349220 cites W2970039673 @default.
- W3092349220 cites W2998166751 @default.
- W3092349220 cites W3009906407 @default.
- W3092349220 doi "https://doi.org/10.1109/dac18072.2020.9218525" @default.
- W3092349220 hasPublicationYear "2020" @default.
- W3092349220 type Work @default.
- W3092349220 sameAs 3092349220 @default.
- W3092349220 citedByCount "2" @default.
- W3092349220 countsByYear W30923492202021 @default.
- W3092349220 crossrefType "proceedings-article" @default.
- W3092349220 hasAuthorship W3092349220A5055445718 @default.
- W3092349220 hasAuthorship W3092349220A5078441163 @default.
- W3092349220 hasAuthorship W3092349220A5083092166 @default.
- W3092349220 hasConcept C105795698 @default.
- W3092349220 hasConcept C113775141 @default.
- W3092349220 hasConcept C119599485 @default.
- W3092349220 hasConcept C127413603 @default.
- W3092349220 hasConcept C132525143 @default.
- W3092349220 hasConcept C153715457 @default.
- W3092349220 hasConcept C154945302 @default.
- W3092349220 hasConcept C186370098 @default.
- W3092349220 hasConcept C26517878 @default.
- W3092349220 hasConcept C2742236 @default.
- W3092349220 hasConcept C2781238097 @default.
- W3092349220 hasConcept C31972630 @default.
- W3092349220 hasConcept C33923547 @default.
- W3092349220 hasConcept C38652104 @default.
- W3092349220 hasConcept C41008148 @default.
- W3092349220 hasConcept C45347329 @default.
- W3092349220 hasConcept C50644808 @default.
- W3092349220 hasConcept C80444323 @default.
- W3092349220 hasConceptScore W3092349220C105795698 @default.
- W3092349220 hasConceptScore W3092349220C113775141 @default.
- W3092349220 hasConceptScore W3092349220C119599485 @default.
- W3092349220 hasConceptScore W3092349220C127413603 @default.
- W3092349220 hasConceptScore W3092349220C132525143 @default.
- W3092349220 hasConceptScore W3092349220C153715457 @default.
- W3092349220 hasConceptScore W3092349220C154945302 @default.
- W3092349220 hasConceptScore W3092349220C186370098 @default.
- W3092349220 hasConceptScore W3092349220C26517878 @default.
- W3092349220 hasConceptScore W3092349220C2742236 @default.
- W3092349220 hasConceptScore W3092349220C2781238097 @default.
- W3092349220 hasConceptScore W3092349220C31972630 @default.
- W3092349220 hasConceptScore W3092349220C33923547 @default.
- W3092349220 hasConceptScore W3092349220C38652104 @default.
- W3092349220 hasConceptScore W3092349220C41008148 @default.
- W3092349220 hasConceptScore W3092349220C45347329 @default.
- W3092349220 hasConceptScore W3092349220C50644808 @default.
- W3092349220 hasConceptScore W3092349220C80444323 @default.
- W3092349220 hasLocation W30923492201 @default.
- W3092349220 hasOpenAccess W3092349220 @default.
- W3092349220 hasPrimaryLocation W30923492201 @default.
- W3092349220 hasRelatedWork W1837097281 @default.
- W3092349220 hasRelatedWork W1966410754 @default.
- W3092349220 hasRelatedWork W1972291043 @default.
- W3092349220 hasRelatedWork W2007544051 @default.
- W3092349220 hasRelatedWork W2016398835 @default.
- W3092349220 hasRelatedWork W2099596012 @default.
- W3092349220 hasRelatedWork W2125175058 @default.
- W3092349220 hasRelatedWork W2363840281 @default.
- W3092349220 hasRelatedWork W2975200075 @default.
- W3092349220 hasRelatedWork W3121394182 @default.
- W3092349220 isParatext "false" @default.
- W3092349220 isRetracted "false" @default.
- W3092349220 magId "3092349220" @default.
- W3092349220 workType "article" @default.