Compact Representation of Mipmapped SVBRDFs via Shared Gaussians

2026-07-30

AI Summary

High-resolution, multi-channel SVBRDF textures and their associated mipmap structures incur substantial storage overhead, and existing compression techniques struggle to simultaneously achieve high compression efficiency, random access, and real-time decoding. This work proposes Gaussian Texture Compression (GTC), which introduces, for the first time, a shared 2D Gaussian representation into SVBRDF compression. By unifying the modeling of redundant structures across both mipmap levels and material channels, GTC enables cross-dimensional Gaussian sharing. The method supports non-neural, real-time decoding and offers flexible rate-distortion trade-offs. Compared to the industrial standard ASTC, GTC significantly improves reconstruction quality and reduces memory footprint while preserving random access capabilities.

Abstract

Spatially-varying BRDFs (SVBRDFs) are central to material representation in computer graphics, but their high-resolution, multi-channel, mipmapped textures impose a substantial storage burden. Existing compression methods face a fundamental trade-off: block-based compression provides random access and hardware-friendly decoding but exploits redundancy only within local blocks; image codecs offer strong rate-distortion performance but are not designed for direct real-time texture access; and neural texture compression achieves high compression ratios but requires neural inference during decoding, which introduces additional runtime overhead, especially on mobile platforms. We present Gaussian Texture Compression (GTC), a compact 2D Gaussian-based representation for mipmapped SVBRDF texture stacks that delivers high-quality compression with flexible rate-distortion trade-offs. Our method is based on a key observation that there are two dominant sources of redundancy in such data: across mip levels and across material maps. Both share a common underlying structure: the same spatial support is reused, with only level- or map-specific information attached. This property naturally suits 2D Gaussians, since each Gaussian explicitly separates its spatial footprint from the values it carries, allowing the footprint to be shared while the values vary per level and per map. Building on this property, GTC shares Gaussians along both redundancy dimensions and is trained via a progressive optimization pipeline. Experiments show that GTC achieves higher reconstruction quality and lower memory usage than ASTC, the industry-standard GPU texture compression format, while supporting random-access, non-neural decoding suitable for real-time rendering.

Problem

• SVBRDF
• texture compression
• mipmapping
• storage efficiency
• real-time rendering

Innovation

• Gaussian Texture Compression
• SVBRDF
• mipmapped textures
• redundancy sharing
• real-time rendering