Hardware Accelerated Neural Block Texture Compression with Cooperative Vectors

Simple item page
dc.contributor.authorBelcour, Laurenten_US
dc.contributor.authorBenyoub, Anisen_US
dc.contributor.editorKnoll, Aaronen_US
dc.contributor.editorPeters, Christophen_US
dc.date.accessioned2025-06-20T07:26:48Z
dc.date.available2025-06-20T07:26:48Z
dc.date.issued2025
dc.description.abstractIn this work, we present an extension to the neural texture compression method of Weinreich and colleagues [WDOHN24]. Like them, we leverage existing block compression methods which permit to use hardware texture filtering to store a neural representation of physically-based rendering (PBR) texture sets (including albedo, normal maps, roughness, etc.). However, we show that low dynamic range block compression formats still make the solution viable. Thanks to this, we show that we can achieve higher compression ratio or higher quality at fixed compression ratio. We improve performance at runtime using a tile based rendering architecture that leverage hardware matrix multiplication engine. Thanks to all this, we render 4k textures sets (9 channels per asset) with anisotropic filtering at 1080p using only 28MB of VRAM per texture set at 0.55ms on an Intel B580.en_US
dc.description.sectionheadersNeural Textures and Encodings
dc.description.seriesinformationHigh-Performance Graphics - Symposium Papers
dc.identifier.doi10.2312/hpg.20251173
dc.identifier.isbn978-3-03868-291-2
dc.identifier.issn2079-8687
dc.identifier.pages6 pages
dc.identifier.urihttps://doi.org/10.2312/hpg.20251173
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/hpg20251173
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleHardware Accelerated Neural Block Texture Compression with Cooperative Vectorsen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
hpg20251173.pdf
Size:
67.16 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1028_mm2.mp4
Size:
161.72 MB
Format:
Video MP4
Download
Collections
High-Performance Graphics 2025 - Symposium Papers