SCAR-GS: Spatial Context Attention for Residuals in Progressive Gaussian Splatting
This incremental improvement addresses storage limitations for deploying 3D Gaussian Splatting in cloud and streaming services.
The paper tackles the high storage requirements of 3D Gaussian Splatting models for novel view synthesis by introducing a progressive codec that uses Residual Vector Quantization and an auto-regressive entropy model to compress primitive features more efficiently.
Recent advances in 3D Gaussian Splatting have allowed for real-time, high-fidelity novel view synthesis. Nonetheless, these models have significant storage requirements for large and medium-sized scenes, hindering their deployment over cloud and streaming services. Some of the most recent progressive compression techniques for these models rely on progressive masking and scalar quantization techniques to reduce the bitrate of Gaussian attributes using spatial context models. While effective, scalar quantization may not optimally capture the correlations of high-dimensional feature vectors, which can potentially limit the rate-distortion performance. In this work, we introduce a novel progressive codec for 3D Gaussian Splatting that replaces traditional methods with a more powerful Residual Vector Quantization approach to compress the primitive features. Our key contribution is an auto-regressive entropy model, guided by a multi-resolution hash grid, that accurately predicts the conditional probability of each successive transmitted index, allowing for coarse and refinement layers to be compressed with high efficiency.