ProtoGS: Efficient and High-Quality Rendering with 3D Gaussian Prototypes
This addresses the efficiency and quality trade-off in 3D Gaussian Splatting for novel view synthesis, enabling better deployment on resource-constrained devices, but it is incremental as it builds on existing compression methods.
The paper tackles the problem of 3D Gaussian Splatting requiring many Gaussian primitives, which limits deployment on lightweight devices, by proposing ProtoGS to learn Gaussian prototypes that reduce the number of Gaussians without sacrificing visual quality, achieving a substantial reduction in Gaussians and high rendering speed while maintaining or enhancing fidelity.
3D Gaussian Splatting (3DGS) has made significant strides in novel view synthesis but is limited by the substantial number of Gaussian primitives required, posing challenges for deployment on lightweight devices. Recent methods address this issue by compressing the storage size of densified Gaussians, yet fail to preserve rendering quality and efficiency. To overcome these limitations, we propose ProtoGS to learn Gaussian prototypes to represent Gaussian primitives, significantly reducing the total Gaussian amount without sacrificing visual quality. Our method directly uses Gaussian prototypes to enable efficient rendering and leverage the resulting reconstruction loss to guide prototype learning. To further optimize memory efficiency during training, we incorporate structure-from-motion (SfM) points as anchor points to group Gaussian primitives. Gaussian prototypes are derived within each group by clustering of K-means, and both the anchor points and the prototypes are optimized jointly. Our experiments on real-world and synthetic datasets prove that we outperform existing methods, achieving a substantial reduction in the number of Gaussians, and enabling high rendering speed while maintaining or even enhancing rendering fidelity.