AdR-Gaussian: Accelerating Gaussian Splatting with Adaptive Radius
arXiv:2409.08669 · doi:10.1145/3680528.3687675
Abstract
3D Gaussian Splatting (3DGS) is a recent explicit 3D representation that has achieved high-quality reconstruction and real-time rendering of complex scenes. However, the rasterization pipeline still suffers from unnecessary overhead resulting from avoidable serial Gaussian culling, and uneven load due to the distinct number of Gaussian to be rendered across pixels, which hinders wider promotion and application of 3DGS. In order to accelerate Gaussian splatting, we propose AdR-Gaussian, which moves part of serial culling in Render stage into the earlier Preprocess stage to enable parallel culling, employing adaptive radius to narrow the rendering pixel range for each Gaussian, and introduces a load balancing method to minimize thread waiting time during the pixel-parallel rendering. Our contributions are threefold, achieving a rendering speed of 310% while maintaining equivalent or even better quality than the state-of-the-art. Firstly, we propose to early cull Gaussian-Tile pairs of low splatting opacity based on an adaptive radius in the Gaussian-parallel Preprocess stage, which reduces the number of affected tile through the Gaussian bounding circle, thus reducing unnecessary overhead and achieving faster rendering speed. Secondly, we further propose early culling based on axis-aligned bounding box for Gaussian splatting, which achieves a more significant reduction in ineffective expenses by accurately calculating the Gaussian size in the 2D directions. Thirdly, we propose a balancing algorithm for pixel thread load, which compresses the information of heavy-load pixels to reduce thread waiting time, and enhance information of light-load pixels to hedge against rendering quality loss. Experiments on three datasets demonstrate that our algorithm can significantly improve the Gaussian Splatting rendering speed.
SIGGRAPH Asia 2024 Conference Papers (SA Conference Papers '24), December 03-06, 2024, Tokyo, Japan
References in corpus (15)
- DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
- Speculative Segmented Sum for Sparse Matrix-Vector Multiplication on Heterogeneous Processors
- 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
- LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
- Gaussian Splatting SLAM
- GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting
- Mip-Splatting: Alias-free 3D Gaussian Splatting
- Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis
- Splatter Image: Ultra-Fast Single-View 3D Reconstruction
- GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians
- EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS
- Compact 3D Gaussian Representation for Radiance Field
- GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering
- HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting
- Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving