Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385964566> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4385964566 abstract "We introduce PoissonNet, an architecture for shape reconstruction that addresses the challenge of recovering 3D shapes from points. Traditional deep neural networks face challenges with common 3D shape discretization techniques due to their computational complexity at higher resolutions. To overcome this, we leverage Fourier Neural Operators (FNOs) to solve the Poisson equation and reconstruct a mesh from oriented point cloud measurements. PoissonNet exhibits two main advantages. First, it enables efficient training on low-resolution data while achieving comparable performance at high-resolution evaluation, thanks to the resolution-agnostic nature of FNOs. This feature allows for one-shot super-resolution. Second, our method surpasses existing approaches in reconstruction quality while being differentiable. Overall, our proposed method not only improves upon the limitations of classical deep neural networks in shape reconstruction but also achieves superior results in terms of reconstruction quality, running time, and resolution flexibility. Furthermore, we demonstrate that the Poisson surface reconstruction problem is well-posed in the limit case by showing a universal approximation theorem for the solution operator of the Poisson equation with distributional data utilizing the Fourier Neural Operator, which provides a theoretical foundation for our numerical results. The code to reproduce the experiments is available on: url{https://github.com/arsenal9971/PoissonNet}." @default.
- W4385964566 created "2023-08-18" @default.
- W4385964566 creator A5067785114 @default.
- W4385964566 creator A5090767423 @default.
- W4385964566 creator A5091856064 @default.
- W4385964566 creator A5092658411 @default.
- W4385964566 date "2023-08-03" @default.
- W4385964566 modified "2023-09-26" @default.
- W4385964566 title "PoissonNet: Resolution-Agnostic 3D Shape Reconstruction using Fourier Neural Operators" @default.
- W4385964566 doi "https://doi.org/10.48550/arxiv.2308.01766" @default.
- W4385964566 hasPublicationYear "2023" @default.
- W4385964566 type Work @default.
- W4385964566 citedByCount "0" @default.
- W4385964566 crossrefType "posted-content" @default.
- W4385964566 hasAuthorship W4385964566A5067785114 @default.
- W4385964566 hasAuthorship W4385964566A5090767423 @default.
- W4385964566 hasAuthorship W4385964566A5091856064 @default.
- W4385964566 hasAuthorship W4385964566A5092658411 @default.
- W4385964566 hasBestOaLocation W43859645661 @default.
- W4385964566 hasConcept C102519508 @default.
- W4385964566 hasConcept C104317684 @default.
- W4385964566 hasConcept C108583219 @default.
- W4385964566 hasConcept C11413529 @default.
- W4385964566 hasConcept C131979681 @default.
- W4385964566 hasConcept C134306372 @default.
- W4385964566 hasConcept C141379421 @default.
- W4385964566 hasConcept C153083717 @default.
- W4385964566 hasConcept C154945302 @default.
- W4385964566 hasConcept C158448853 @default.
- W4385964566 hasConcept C17020691 @default.
- W4385964566 hasConcept C185592680 @default.
- W4385964566 hasConcept C202615002 @default.
- W4385964566 hasConcept C20885615 @default.
- W4385964566 hasConcept C2524010 @default.
- W4385964566 hasConcept C2776799497 @default.
- W4385964566 hasConcept C33923547 @default.
- W4385964566 hasConcept C41008148 @default.
- W4385964566 hasConcept C50644808 @default.
- W4385964566 hasConcept C55493867 @default.
- W4385964566 hasConcept C73000952 @default.
- W4385964566 hasConcept C86339819 @default.
- W4385964566 hasConcept C96716743 @default.
- W4385964566 hasConceptScore W4385964566C102519508 @default.
- W4385964566 hasConceptScore W4385964566C104317684 @default.
- W4385964566 hasConceptScore W4385964566C108583219 @default.
- W4385964566 hasConceptScore W4385964566C11413529 @default.
- W4385964566 hasConceptScore W4385964566C131979681 @default.
- W4385964566 hasConceptScore W4385964566C134306372 @default.
- W4385964566 hasConceptScore W4385964566C141379421 @default.
- W4385964566 hasConceptScore W4385964566C153083717 @default.
- W4385964566 hasConceptScore W4385964566C154945302 @default.
- W4385964566 hasConceptScore W4385964566C158448853 @default.
- W4385964566 hasConceptScore W4385964566C17020691 @default.
- W4385964566 hasConceptScore W4385964566C185592680 @default.
- W4385964566 hasConceptScore W4385964566C202615002 @default.
- W4385964566 hasConceptScore W4385964566C20885615 @default.
- W4385964566 hasConceptScore W4385964566C2524010 @default.
- W4385964566 hasConceptScore W4385964566C2776799497 @default.
- W4385964566 hasConceptScore W4385964566C33923547 @default.
- W4385964566 hasConceptScore W4385964566C41008148 @default.
- W4385964566 hasConceptScore W4385964566C50644808 @default.
- W4385964566 hasConceptScore W4385964566C55493867 @default.
- W4385964566 hasConceptScore W4385964566C73000952 @default.
- W4385964566 hasConceptScore W4385964566C86339819 @default.
- W4385964566 hasConceptScore W4385964566C96716743 @default.
- W4385964566 hasLocation W43859645661 @default.
- W4385964566 hasOpenAccess W4385964566 @default.
- W4385964566 hasPrimaryLocation W43859645661 @default.
- W4385964566 hasRelatedWork W2566809385 @default.
- W4385964566 hasRelatedWork W2989990169 @default.
- W4385964566 hasRelatedWork W3034196047 @default.
- W4385964566 hasRelatedWork W3172995512 @default.
- W4385964566 hasRelatedWork W3214168277 @default.
- W4385964566 hasRelatedWork W4288018482 @default.
- W4385964566 hasRelatedWork W4289525220 @default.
- W4385964566 hasRelatedWork W4311224126 @default.
- W4385964566 hasRelatedWork W4367461233 @default.
- W4385964566 hasRelatedWork W4382283225 @default.
- W4385964566 isParatext "false" @default.
- W4385964566 isRetracted "false" @default.
- W4385964566 workType "article" @default.