Search papers, labs, and topics across Lattice.
This paper introduces 3DGBGS, an innovative framework that enhances novel-view synthesis by integrating adaptive granular ball organization into anchor-based 3D Gaussian Splatting. By intelligently partitioning sparse SfM point clouds into granular balls of varying sizes, the method effectively balances model compactness and rendering quality, addressing limitations of traditional fixed voxelization approaches. Experimental results demonstrate that 3DGBGS significantly reduces the number of anchors and model storage while preserving high rendering fidelity across multiple benchmarks.
Reducing model storage by nearly 10% without sacrificing rendering quality, 3DGBGS redefines efficiency in novel-view synthesis.
Three-dimensional Gaussian Splatting (3DGS) enables high-quality real-time novel-view synthesis through explicit Gaussian primitives and differentiable rasterization. 3DGS and Granular Ball Computing (GBC), proposed in 2019, share a natural compatibility in adaptive representation. The efficiency of 3DGS partly stems from a coarse-to-fine and on-demand refinement process that draws on the generation principle of GBC. This connection motivates us to further introduce adaptive granular ball organization into anchor-based 3DGS. Existing anchor-based methods typically construct anchors from sparse SfM point clouds through fixed voxelization, which cannot adequately adapt to spatially non-uniform point distributions and leads to a trade-off among anchor count, model compactness, and rendering quality. To address this issue, we propose 3DGBGS (3D Granular Ball Gaussian Splatting), a compact anchor-based framework for novel-view synthesis. 3DGBGS adaptively partitions SfM point clouds into 3D granular balls, using larger balls to compactly represent smooth and redundant regions and smaller balls to preserve complex geometry and local details. Based on this representation, Granular Ball Anchor Initialization (GBAI) uses granular ball centers to initialize compact anchor positions, while the Granular Ball Scale Prior (GBSP) exploits granular ball radii to provide local scale priors for Gaussian generation. Experiments on four benchmarks show that 3DGBGS reduces initial and final anchors by 37.1% and 10.0%, respectively, and model storage by 9.8% on average, while maintaining comparable rendering quality.
