Search papers, labs, and topics across Lattice.
This paper addresses the high memory requirements of 3D Gaussian Splatting (3DGS) by introducing a novel compression method for spherical harmonic (SH) color coefficients that leverages GPU-friendly texture coding. By utilizing dedicated hardware acceleration and a bit-rate control strategy, the proposed approach enables efficient parallel decoding and rendering while maintaining visual quality. Experimental results demonstrate that the new compression techniques outperform traditional 2D texture methods, achieving significant memory savings without compromising the rendering performance of 3DGS scenes.
GPU-optimized texture compression can drastically reduce memory usage in 3D Gaussian Splatting while preserving visual fidelity, revolutionizing scene rendering efficiency.
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.