用自适应颗粒球优化3D高斯点云，更紧凑且保细节。
3DGBGS: 3D Granular Ball Gaussian Splatting for Compact Novel View Synthesis
- 基于颗粒球动态分块点云，大块压缩平滑区，小块保留细节。
- 相比基线减少37.1%初始锚点、10.0%最终锚点，存储降9.8%。
- 适合追求模型轻量化与高质量渲染的视觉重建应用。
三维高斯溅射（3DGS）通过显式高斯原语和可微光栅化实现高质量实时新视角合成。2019年提出的颗粒球计算（GBC）与3DGS在自适应表示上具有天然兼容性，3DGS的效率部分源于基于GBC生成原理的粗到精、按需细化过程。这一联系促使我们进一步将自适应颗粒球结构引入基于锚点的3DGS。现有锚点方法通常通过固定体素化从稀疏SfM点云构建锚点，难以适应空间分布不均的情况，导致锚点数量、模型紧凑性与渲染质量间的权衡。为此，提出3DGBGS（3D颗粒球高斯溅射），一种紧凑的基于锚点的新视角合成框架。3DGBGS自适应地将SfM点云划分为3D颗粒球：以较大球体紧凑表示平滑冗余区域，以较小球体保留复杂几何与局部细节。在此表示基础上，颗粒球锚点初始化（GBAI）利用颗粒球中心初始化紧凑锚点位置，颗粒球尺度先验（GBSP）则利用颗粒球半径为高斯生成提供局部尺度先验。四个基准测试实验表明，3DGBGS平均减少初始锚点37.1%、最终锚点10.0%，模型存储降低9.8%，同时保持相当的渲染质量。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。