Fujieda, ShinHarada, TakahiroHardeberg, Jon YngveRushmeier, Holly2024-08-282024-08-282024978-3-03868-264-62309-5059https://doi.org/10.2312/mam.20241178https://diglib.eg.org/handle/10.2312/mam20241178Block 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.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Image compression; Texturing; Image representationsComputing methodologies → Image compressionTexturingImage representations10.2312/mam.202411784 pages