AdaGScale: Viewpoint-Adaptive Gaussian Scaling in 3D Gaussian Splatting to Reduce Gaussian-Tile Pairs

TL;DR

AdaGScale introduces a viewpoint-adaptive Gaussian scaling method that reduces Gaussian-tile pairs in 3D Gaussian Splatting, significantly boosting rendering speed with minimal quality loss.

Contribution

It proposes a novel adaptive scaling technique based on color contribution to efficiently reduce Gaussian-tile pairs in 3D-GS rendering.

Findings

Achieves a 13.8x speedup over original 3D-GS on GPU.

Maintains image quality with only 0.5 dB PSNR degradation.

Effectively reduces Gaussian-tile pairs by adaptive scaling.

Abstract

Reducing the number of Gaussian-tile pairs is one of the most promising approaches to improve 3D Gaussian Splatting (3D-GS) rendering speed on GPUs. However, the importance difference existing among Gaussian-tile pairs has never been considered in the previous works. In this paper, we propose AdaGScale, a novel viewpoint-adaptive Gaussian scaling technique for reducing the number of Gaussian-tile pairs. AdaGScale is based on the observation that the peripheral tiles located far from Gaussian center contribute negligibly to pixel color accumulation. This suggests an opportunity for reducing the number of Gaussian-tile pairs based on color contribution. AdaGScale efficiently estimates the color contribution in the peripheral region of each Gaussian during a preprocessing stage and adaptively scales its size based on the peripheral score. As a result, Gaussians with lower importance intersect with fewer tiles during the intersection test, which improves rendering speed while maintaining image quality. The adjusted size is used only for tile intersection test, and the original size is retained during color accumulation to preserve visual fidelity. Experimental results show that AdaGScale achieves a geometric mean speedup of 13.8x over original 3D-GS on a GPU, with only about 0.5 dB degradation in PSNR on city-scale scenes.