FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2986559888> ?p ?o ?g. }

• W2986559888 endingPage "13" @default.
• W2986559888 startingPage "1" @default.
• W2986559888 abstract "Monte Carlo (MC) methods for light transport simulation are flexible and general but typically suffer from high variance and slow convergence. Gradientdomain rendering alleviates this problem by additionally generating image gradients and reformulating rendering as a screened Poisson image reconstruction problem. To improve the quality and performance of the reconstruction, we propose a novel and practical deep learning based approach in this paper. The core of our approach is a multi-branch auto-encoder, termed GradNet, which end-to-end learns a mapping from a noisy input image and its corresponding image gradients to a high-quality image with low variance. Once trained, our network is fast to evaluate and does not require manual parameter tweaking. Due to the difficulty in preparing ground-truth images for training, we design and train our network in a completely unsupervised manner by learning directly from the input data. This is the first solution incorporating unsupervised deep learning into the gradient-domain rendering framework. The loss function is defined as an energy function including a data fidelity term and a gradient fidelity term. To further reduce the noise of the reconstructed image, the loss function is reinforced by adding a regularizer constructed from selected rendering-specific features. We demonstrate that our method improves the reconstruction quality for a diverse set of scenes, and reconstructing a high-resolution image takes far less than one second on a recent GPU." @default.
• W2986559888 created "2019-11-22" @default.
• W2986559888 creator A5009275869 @default.
• W2986559888 creator A5017493517 @default.
• W2986559888 creator A5020752454 @default.
• W2986559888 creator A5023175239 @default.
• W2986559888 creator A5037025481 @default.
• W2986559888 creator A5041712189 @default.
• W2986559888 creator A5042385843 @default.
• W2986559888 date "2019-11-08" @default.
• W2986559888 modified "2023-10-16" @default.
• W2986559888 title "GradNet" @default.
• W2986559888 cites W1836967730 @default.
• W2986559888 cites W1901129140 @default.
• W2986559888 cites W1976454752 @default.
• W2986559888 cites W1977778188 @default.
• W2986559888 cites W1984696318 @default.
• W2986559888 cites W1997784634 @default.
• W2986559888 cites W2020681231 @default.
• W2986559888 cites W2037735934 @default.
• W2986559888 cites W2047913565 @default.
• W2986559888 cites W2100495367 @default.
• W2986559888 cites W2102727143 @default.
• W2986559888 cites W2135623116 @default.
• W2986559888 cites W2136396015 @default.
• W2986559888 cites W2151035893 @default.
• W2986559888 cites W2161328579 @default.
• W2986559888 cites W2207744012 @default.
• W2986559888 cites W2407358168 @default.
• W2986559888 cites W2466064361 @default.
• W2986559888 cites W2550375358 @default.
• W2986559888 cites W2553326439 @default.
• W2986559888 cites W2562637781 @default.
• W2986559888 cites W2738449271 @default.
• W2986559888 cites W2768744879 @default.
• W2986559888 cites W2810300686 @default.
• W2986559888 cites W2811168853 @default.
• W2986559888 cites W2884298752 @default.
• W2986559888 cites W2898414622 @default.
• W2986559888 cites W2919115771 @default.
• W2986559888 cites W2961552930 @default.
• W2986559888 cites W2963767233 @default.
• W2986559888 cites W4297833218 @default.
• W2986559888 doi "https://doi.org/10.1145/3355089.3356538" @default.
• W2986559888 hasPublicationYear "2019" @default.
• W2986559888 type Work @default.
• W2986559888 sameAs 2986559888 @default.
• W2986559888 citedByCount "12" @default.
• W2986559888 countsByYear W29865598882020 @default.
• W2986559888 countsByYear W29865598882021 @default.
• W2986559888 countsByYear W29865598882022 @default.
• W2986559888 crossrefType "journal-article" @default.
• W2986559888 hasAuthorship W2986559888A5009275869 @default.
• W2986559888 hasAuthorship W2986559888A5017493517 @default.
• W2986559888 hasAuthorship W2986559888A5020752454 @default.
• W2986559888 hasAuthorship W2986559888A5023175239 @default.
• W2986559888 hasAuthorship W2986559888A5037025481 @default.
• W2986559888 hasAuthorship W2986559888A5041712189 @default.
• W2986559888 hasAuthorship W2986559888A5042385843 @default.
• W2986559888 hasConcept C11413529 @default.
• W2986559888 hasConcept C115961682 @default.
• W2986559888 hasConcept C146849305 @default.
• W2986559888 hasConcept C154945302 @default.
• W2986559888 hasConcept C205711294 @default.
• W2986559888 hasConcept C2776459999 @default.
• W2986559888 hasConcept C31972630 @default.
• W2986559888 hasConcept C41008148 @default.
• W2986559888 hasConcept C55020928 @default.
• W2986559888 hasConcept C76155785 @default.
• W2986559888 hasConcept C89720835 @default.
• W2986559888 hasConceptScore W2986559888C11413529 @default.
• W2986559888 hasConceptScore W2986559888C115961682 @default.
• W2986559888 hasConceptScore W2986559888C146849305 @default.
• W2986559888 hasConceptScore W2986559888C154945302 @default.
• W2986559888 hasConceptScore W2986559888C205711294 @default.
• W2986559888 hasConceptScore W2986559888C2776459999 @default.
• W2986559888 hasConceptScore W2986559888C31972630 @default.
• W2986559888 hasConceptScore W2986559888C41008148 @default.
• W2986559888 hasConceptScore W2986559888C55020928 @default.
• W2986559888 hasConceptScore W2986559888C76155785 @default.
• W2986559888 hasConceptScore W2986559888C89720835 @default.
• W2986559888 hasFunder F4320321001 @default.
• W2986559888 hasIssue "6" @default.
• W2986559888 hasLocation W29865598881 @default.
• W2986559888 hasOpenAccess W2986559888 @default.
• W2986559888 hasPrimaryLocation W29865598881 @default.
• W2986559888 hasRelatedWork W1503414886 @default.
• W2986559888 hasRelatedWork W1632903234 @default.
• W2986559888 hasRelatedWork W1863533157 @default.
• W2986559888 hasRelatedWork W2048402902 @default.
• W2986559888 hasRelatedWork W2087353037 @default.
• W2986559888 hasRelatedWork W2093747323 @default.
• W2986559888 hasRelatedWork W2143214896 @default.
• W2986559888 hasRelatedWork W2574052219 @default.
• W2986559888 hasRelatedWork W2740010476 @default.
• W2986559888 hasRelatedWork W3182299699 @default.
• W2986559888 hasVolume "38" @default.
• W2986559888 isParatext "false" @default.

• next