Compression of 3D Gaussian Splatting Data Using GPU-friendly Graphics Texture Coding

2026-07-15

AI Summary

This work addresses the high memory overhead of 3D Gaussian Splatting (3DGS) caused by its extensive spherical harmonics coefficients, a challenge exacerbated by existing compression methods that fail to leverage GPU parallel decoding efficiently. To overcome this limitation, the study introduces the first application of GPU-friendly BC1/BC7 texture compression formats to 3DGS coefficient compression. The proposed approach integrates color-clustering-guided primitive reordering with a rate-control strategy supporting random access. This enables significant reductions in storage requirements with negligible visual degradation while facilitating efficient parallel decompression and real-time rendering directly on the GPU, thereby achieving an effective balance between compression efficiency and rendering performance.

Abstract

Techniques for modeling 3D scenes from image collections, such as 3D Gaussian Splatting (3DGS), are capable of generating high-quality novel views by leveraging graphics primitives with view-dependent appearance. In 3DGS, spherical harmonic (SH) are employed to model view-dependent color, resulting in a large number of SH coefficients per primitive and large memory requirements. While compression approaches have been proposed to mitigate this problem, they do not exploit the capabilities of modern Graphics Processing Units (GPUs) for parallel decoding and rendering. In this paper, we propose a method for compressing SH color coefficients using texture compression schemes specifically designed for efficient parallel GPU decoding and supported by dedicated hardware acceleration. It is shown that those methods can compress color coefficients more effectively than 2D textures by exploiting the fact that primitives can be locally grouped and reordered according to color. Furthermore, we introduce a bit-rate control strategy that preserves random access, enabling large-scale parallelization without compromising rendering performance. Experimental results using BC1 and BC7 texture compression formats show that GPU-based decompression can be achieved with negligible or imperceptible degradation in the visual quality of rendered 3DGS scenes.

Problem

• 3D Gaussian Splatting
• Spherical Harmonics
• GPU-friendly compression
• Texture Compression
• Memory Efficiency

Innovation

• 3D Gaussian Splatting
• texture compression
• GPU acceleration
• spherical harmonics
• random access