Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328007150> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4328007150 endingPage "14" @default.
- W4328007150 startingPage "1" @default.
- W4328007150 abstract "Although neural supersampling has achieved great success in various applications for improving image quality, it is still difficult to apply it to a wide range of real-time rendering applications due to the high computational power demand. Most existing methods are computationally expensive and require high-performance hardware, preventing their use on platforms with limited hardware, such as smartphones. To this end, we propose a new supersampling framework for real-time rendering applications to reconstruct a high-quality image out of a low-resolution one, which is sufficiently lightweight to run on smartphones within a real-time budget. Our model takes as input the renderer-generated low resolution content and produces high resolution and anti-aliased results. To maximize sampling efficiency, we propose using an alternate sub-pixel sample pattern during the rasterization process. This allows us to create a relatively small reconstruction model while maintaining high image quality. By accumulating new samples into a high-resolution history buffer, an efficient history check and re-usage scheme is introduced to improve temporal stability. To our knowledge, this is the first research in pushing real-time neural supersampling on mobile devices. Due to the absence of training data, we present a new dataset containing 57 training and test sequences from three game scenes. Furthermore, based on the rendered motion vectors and a visual perception study, we introduce a new metric called inter-frame structural similarity (IF-SSIM) to quantitatively measure the temporal stability of rendered videos. Extensive evaluations demonstrate that our supersampling model outperforms existing or alternative solutions in both performance and temporal stability." @default.
- W4328007150 created "2023-03-22" @default.
- W4328007150 creator A5007960405 @default.
- W4328007150 creator A5015279307 @default.
- W4328007150 creator A5018230219 @default.
- W4328007150 creator A5024916524 @default.
- W4328007150 creator A5032447166 @default.
- W4328007150 creator A5050061175 @default.
- W4328007150 creator A5053891639 @default.
- W4328007150 creator A5085126199 @default.
- W4328007150 date "2023-01-01" @default.
- W4328007150 modified "2023-10-16" @default.
- W4328007150 title "MNSS: Neural Supersampling Framework for Real-Time Rendering on Mobile Devices" @default.
- W4328007150 doi "https://doi.org/10.1109/tvcg.2023.3259141" @default.
- W4328007150 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37030766" @default.
- W4328007150 hasPublicationYear "2023" @default.
- W4328007150 type Work @default.
- W4328007150 citedByCount "0" @default.
- W4328007150 crossrefType "journal-article" @default.
- W4328007150 hasAuthorship W4328007150A5007960405 @default.
- W4328007150 hasAuthorship W4328007150A5015279307 @default.
- W4328007150 hasAuthorship W4328007150A5018230219 @default.
- W4328007150 hasAuthorship W4328007150A5024916524 @default.
- W4328007150 hasAuthorship W4328007150A5032447166 @default.
- W4328007150 hasAuthorship W4328007150A5050061175 @default.
- W4328007150 hasAuthorship W4328007150A5053891639 @default.
- W4328007150 hasAuthorship W4328007150A5085126199 @default.
- W4328007150 hasConcept C111919701 @default.
- W4328007150 hasConcept C154945302 @default.
- W4328007150 hasConcept C160633673 @default.
- W4328007150 hasConcept C164597639 @default.
- W4328007150 hasConcept C186967261 @default.
- W4328007150 hasConcept C205711294 @default.
- W4328007150 hasConcept C31972630 @default.
- W4328007150 hasConcept C3261483 @default.
- W4328007150 hasConcept C41008148 @default.
- W4328007150 hasConcept C71597744 @default.
- W4328007150 hasConcept C79403827 @default.
- W4328007150 hasConceptScore W4328007150C111919701 @default.
- W4328007150 hasConceptScore W4328007150C154945302 @default.
- W4328007150 hasConceptScore W4328007150C160633673 @default.
- W4328007150 hasConceptScore W4328007150C164597639 @default.
- W4328007150 hasConceptScore W4328007150C186967261 @default.
- W4328007150 hasConceptScore W4328007150C205711294 @default.
- W4328007150 hasConceptScore W4328007150C31972630 @default.
- W4328007150 hasConceptScore W4328007150C3261483 @default.
- W4328007150 hasConceptScore W4328007150C41008148 @default.
- W4328007150 hasConceptScore W4328007150C71597744 @default.
- W4328007150 hasConceptScore W4328007150C79403827 @default.
- W4328007150 hasLocation W43280071501 @default.
- W4328007150 hasLocation W43280071502 @default.
- W4328007150 hasOpenAccess W4328007150 @default.
- W4328007150 hasPrimaryLocation W43280071501 @default.
- W4328007150 hasRelatedWork W121273120 @default.
- W4328007150 hasRelatedWork W2048402902 @default.
- W4328007150 hasRelatedWork W2090093270 @default.
- W4328007150 hasRelatedWork W2337415362 @default.
- W4328007150 hasRelatedWork W2397531349 @default.
- W4328007150 hasRelatedWork W2779438614 @default.
- W4328007150 hasRelatedWork W2945599696 @default.
- W4328007150 hasRelatedWork W4312857205 @default.
- W4328007150 hasRelatedWork W4328007150 @default.
- W4328007150 hasRelatedWork W3182299699 @default.
- W4328007150 isParatext "false" @default.
- W4328007150 isRetracted "false" @default.
- W4328007150 workType "article" @default.