Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis

By Simon Niedermayr, Josef Stumpfegger, Rüdiger Westermann. Computer Vision and Pattern Recognition, 2023

296 citations recorded by the source corpus.

Recently, high-fidelity scene reconstruction with an optimized 3D Gaussian splat representation has been introducedfor novel view synthesis from sparse image sets. Making such representations suitable for applications like network streaming and rendering on low-power devices requires significantly reduced memory consumption as well as improved rendering efficiency. We propose a compressed 3D Gaussian splat representation that utilizes sensitivity-aware vector clustering with quantization-aware training to compress directional colors and Gaussian parameters. The learned codebooks have low bitrates and achieve a compression rate of up to 31 × on real-world scenes with only minimal degradation of visual quality. We demonstrate that the compressed splat representation can be efficiently rendered with hardware rasterization on lightweight GPUs at up to 4 × higher framerates than reported via an optimized GPU compute pipeline. Extensive experiments across multiple datasets demonstrate the robustness and rendering speed of the proposed approach.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/dec87056f778ae48f5129a9ad73b186037b6be78

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

1. Dejia Xu
2. Zhangyang Wang
3. Zehao Zhu
4. Kairun Wen
5. Kevin Wang
6. Zhiwen Fan

In Computer Vision and Pattern Recognition

1. Dejia Xu
2. Zhangyang Wang
3. Zehao Zhu
4. Kairun Wen
5. Kevin Wang
6. Zhiwen Fan
7. Wenguan Wang
8. Guikun Chen

Citations in the corpus

• Recent advances in 3D Gaussian splatting (2024, unknown): “Quantitative reconstruction results and sizes of 3D scenes after compression are shown in Table 2.”
• LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS (2023, background): “Model Pruning and Vector Quantization Model pruning involves reducing the complexity of a neural network by eliminating non-significant parameters to maintain a balance between performance and resource utilization.”
• Multi-Scale Gaussian-Language Map for Zero-shot Embodied Navigation and Reasoning (2026, unknown): “The original 3DGS [15, 24, 54] aims to render novel views from multi-view images.”