GaussianForest: Hierarchical-Hybrid 3D Gaussian Splatting for Compressed Scene Modeling
This addresses the storage bottleneck for 3D Gaussian Splatting applications, enabling more efficient scene modeling, though it appears incremental as it builds directly on existing methods.
The paper tackles the storage challenge of 3D Gaussian Splatting for novel-view synthesis by introducing Gaussian-Forest, a hierarchical-hybrid framework that reduces parameters through shared implicit attributes and adaptive strategies, achieving over 10x compression while maintaining comparable speed and quality.
The field of novel-view synthesis has recently witnessed the emergence of 3D Gaussian Splatting, which represents scenes in a point-based manner and renders through rasterization. This methodology, in contrast to Radiance Fields that rely on ray tracing, demonstrates superior rendering quality and speed. However, the explicit and unstructured nature of 3D Gaussians poses a significant storage challenge, impeding its broader application. To address this challenge, we introduce the Gaussian-Forest modeling framework, which hierarchically represents a scene as a forest of hybrid 3D Gaussians. Each hybrid Gaussian retains its unique explicit attributes while sharing implicit ones with its sibling Gaussians, thus optimizing parameterization with significantly fewer variables. Moreover, adaptive growth and pruning strategies are designed, ensuring detailed representation in complex regions and a notable reduction in the number of required Gaussians. Extensive experiments demonstrate that Gaussian-Forest not only maintains comparable speed and quality but also achieves a compression rate surpassing 10 times, marking a significant advancement in efficient scene modeling. Codes will be available at https://github.com/Xian-Bei/GaussianForest.