Deep and Fast Approximate Order Independent Transparency

Simple item page
dc.contributor.authorTsopouridis, Grigorisen_US
dc.contributor.authorVasilakis, Andreas A.en_US
dc.contributor.authorFudos, Ioannisen_US
dc.contributor.editorAlliez, Pierreen_US
dc.contributor.editorWimmer, Michaelen_US
dc.date.accessioned2024-12-19T11:15:54Z
dc.date.available2024-12-19T11:15:54Z
dc.date.issued2024
dc.description.abstractWe present a machine learning approach for efficiently computing order independent transparency (OIT) by deploying a light weight neural network implemented fully on shaders. Our method is fast, requires a small constant amount of memory (depends only on the screen resolution and not on the number of triangles or transparent layers), is more accurate as compared to previous approximate methods, works for every scene without setup and is portable to all platforms running even with commodity GPUs. Our method requires a rendering pass to extract all features that are subsequently used to predict the overall OIT pixel colour with a pre‐trained neural network. We provide a comparative experimental evaluation and shader source code of all methods for reproduction of the experiments.en_US
dc.description.number6
dc.description.sectionheadersMajor Revision from Pacific Graphics
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15071
dc.identifier.pages14 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15071
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15071
dc.publisher© 2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.en_US
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectrendering
dc.subjectvisibility determination
dc.subjectorder‐independent transparency
dc.subjectreal‐time rendering
dc.subjectdeep learning
dc.titleDeep and Fast Approximate Order Independent Transparencyen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
21_cgf15071.pdf
Size:
13.68 MB
Format:
Adobe Portable Document Format
Download
Collections
43-Issue 6