Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians
This work addresses the challenge of constrained Gaussian representation for efficient scene rendering in computer graphics, though it appears incremental as it builds on existing Gaussian-Splatting methods.
The paper tackles the problem of inefficient spatial distribution in Gaussian-based scene representation by introducing densification and simplification strategies, resulting in significant improvements in rendering quality, resource consumption, and storage compression across various datasets.
In this study, we explore the challenge of efficiently representing scenes with a constrained number of Gaussians. Our analysis shifts from traditional graphics and 2D computer vision to the perspective of point clouds, highlighting the inefficient spatial distribution of Gaussian representation as a key limitation in model performance. To address this, we introduce strategies for densification including blur split and depth reinitialization, and simplification through intersection preserving and sampling. These techniques reorganize the spatial positions of the Gaussians, resulting in significant improvements across various datasets and benchmarks in terms of rendering quality, resource consumption, and storage compression. Our Mini-Splatting integrates seamlessly with the original rasterization pipeline, providing a strong baseline for future research in Gaussian-Splatting-based works. \href{https://github.com/fatPeter/mini-splatting}{Code is available}.