Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286750544> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4286750544 abstract "Novel view synthesis has recently been revolutionized by learning neural radiance fields directly from sparse observations. However, rendering images with this new paradigm is slow due to the fact that an accurate quadrature of the volume rendering equation requires a large number of samples for each ray. Previous work has mainly focused on speeding up the network evaluations that are associated with each sample point, e.g., via caching of radiance values into explicit spatial data structures, but this comes at the expense of model compactness. In this paper, we propose a novel dual-network architecture that takes an orthogonal direction by learning how to best reduce the number of required sample points. To this end, we split our network into a sampling and shading network that are jointly trained. Our training scheme employs fixed sample positions along each ray, and incrementally introduces sparsity throughout training to achieve high quality even at low sample counts. After fine-tuning with the target number of samples, the resulting compact neural representation can be rendered in real-time. Our experiments demonstrate that our approach outperforms concurrent compact neural representations in terms of quality and frame rate and performs on par with highly efficient hybrid representations. Code and supplementary material is available at https://thomasneff.github.io/adanerf." @default.
- W4286750544 created "2022-07-23" @default.
- W4286750544 creator A5005789795 @default.
- W4286750544 creator A5014594342 @default.
- W4286750544 creator A5050363226 @default.
- W4286750544 creator A5054615124 @default.
- W4286750544 creator A5076488365 @default.
- W4286750544 date "2022-07-21" @default.
- W4286750544 modified "2023-09-27" @default.
- W4286750544 title "AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fields" @default.
- W4286750544 doi "https://doi.org/10.48550/arxiv.2207.10312" @default.
- W4286750544 hasPublicationYear "2022" @default.
- W4286750544 type Work @default.
- W4286750544 citedByCount "0" @default.
- W4286750544 crossrefType "posted-content" @default.
- W4286750544 hasAuthorship W4286750544A5005789795 @default.
- W4286750544 hasAuthorship W4286750544A5014594342 @default.
- W4286750544 hasAuthorship W4286750544A5050363226 @default.
- W4286750544 hasAuthorship W4286750544A5054615124 @default.
- W4286750544 hasAuthorship W4286750544A5076488365 @default.
- W4286750544 hasBestOaLocation W42867505441 @default.
- W4286750544 hasConcept C105795698 @default.
- W4286750544 hasConcept C11413529 @default.
- W4286750544 hasConcept C127313418 @default.
- W4286750544 hasConcept C154945302 @default.
- W4286750544 hasConcept C185592680 @default.
- W4286750544 hasConcept C19499675 @default.
- W4286750544 hasConcept C198531522 @default.
- W4286750544 hasConcept C205711294 @default.
- W4286750544 hasConcept C23690007 @default.
- W4286750544 hasConcept C2781395549 @default.
- W4286750544 hasConcept C31972630 @default.
- W4286750544 hasConcept C33923547 @default.
- W4286750544 hasConcept C41008148 @default.
- W4286750544 hasConcept C43617362 @default.
- W4286750544 hasConcept C50644808 @default.
- W4286750544 hasConcept C62649853 @default.
- W4286750544 hasConcept C84211073 @default.
- W4286750544 hasConcept C89720835 @default.
- W4286750544 hasConceptScore W4286750544C105795698 @default.
- W4286750544 hasConceptScore W4286750544C11413529 @default.
- W4286750544 hasConceptScore W4286750544C127313418 @default.
- W4286750544 hasConceptScore W4286750544C154945302 @default.
- W4286750544 hasConceptScore W4286750544C185592680 @default.
- W4286750544 hasConceptScore W4286750544C19499675 @default.
- W4286750544 hasConceptScore W4286750544C198531522 @default.
- W4286750544 hasConceptScore W4286750544C205711294 @default.
- W4286750544 hasConceptScore W4286750544C23690007 @default.
- W4286750544 hasConceptScore W4286750544C2781395549 @default.
- W4286750544 hasConceptScore W4286750544C31972630 @default.
- W4286750544 hasConceptScore W4286750544C33923547 @default.
- W4286750544 hasConceptScore W4286750544C41008148 @default.
- W4286750544 hasConceptScore W4286750544C43617362 @default.
- W4286750544 hasConceptScore W4286750544C50644808 @default.
- W4286750544 hasConceptScore W4286750544C62649853 @default.
- W4286750544 hasConceptScore W4286750544C84211073 @default.
- W4286750544 hasConceptScore W4286750544C89720835 @default.
- W4286750544 hasLocation W42867505441 @default.
- W4286750544 hasOpenAccess W4286750544 @default.
- W4286750544 hasPrimaryLocation W42867505441 @default.
- W4286750544 hasRelatedWork W10809924 @default.
- W4286750544 hasRelatedWork W12428677 @default.
- W4286750544 hasRelatedWork W14066574 @default.
- W4286750544 hasRelatedWork W14306054 @default.
- W4286750544 hasRelatedWork W2009874 @default.
- W4286750544 hasRelatedWork W2433769 @default.
- W4286750544 hasRelatedWork W3781714 @default.
- W4286750544 hasRelatedWork W8067959 @default.
- W4286750544 hasRelatedWork W819137 @default.
- W4286750544 hasRelatedWork W8208422 @default.
- W4286750544 isParatext "false" @default.
- W4286750544 isRetracted "false" @default.
- W4286750544 workType "article" @default.