Neural Texture Block Compression
dc.contributor.author | Fujieda, Shin | en_US |
dc.contributor.author | Harada, Takahiro | en_US |
dc.contributor.editor | Hardeberg, Jon Yngve | en_US |
dc.contributor.editor | Rushmeier, Holly | en_US |
dc.date.accessioned | 2024-08-28T06:31:59Z | |
dc.date.available | 2024-08-28T06:31:59Z | |
dc.date.issued | 2024 | |
dc.description.abstract | Block compression is a widely used technique to compress textures in real-time graphics applications, offering a reduction in storage size. However, their storage efficiency is constrained by the fixed compression ratio, which substantially increases storage size when hundreds of high-quality textures are required. In this paper, we propose a novel block texture compression method with neural networks, Neural Texture Block Compression (NTBC). NTBC learns the mapping from uncompressed textures to block-compressed textures, which allows for significantly reduced storage costs without any change in the shaders. Our experiments show that NTBC can achieve reasonable-quality results with up to about 45% less storage footprint, preserving real-time performance with a modest computational overhead at the texture loading phase in the graphics pipeline. | en_US |
dc.description.sectionheaders | Representation / Capture / Wave Optics | |
dc.description.seriesinformation | Workshop on Material Appearance Modeling | |
dc.description.seriesinformation | Joint MAM - MANER Conference - Material Appearance Network for Education and Research | |
dc.identifier.doi | 10.2312/mam.20241178 | |
dc.identifier.isbn | 978-3-03868-264-6 | |
dc.identifier.issn | 2309-5059 | |
dc.identifier.pages | 4 pages | |
dc.identifier.uri | https://doi.org/10.2312/mam.20241178 | |
dc.identifier.uri | https://diglib.eg.org/handle/10.2312/mam20241178 | |
dc.publisher | The Eurographics Association | en_US |
dc.rights | Attribution 4.0 International License | |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
dc.subject | CCS Concepts: Computing methodologies → Image compression; Texturing; Image representations | |
dc.subject | Computing methodologies → Image compression | |
dc.subject | Texturing | |
dc.subject | Image representations | |
dc.title | Neural Texture Block Compression | en_US |
Files
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- mam20241178.pdf
- Size:
- 2.9 MB
- Format:
- Adobe Portable Document Format