用3D几何信息高效剪枝并优化3D高斯溅射，提升渲染效率。
PointSplat: Efficient Geometry-Driven Pruning and Transformer Refinement for 3D Gaussian Splatting
- 基于3D属性排序高斯点，无需2D图像辅助剪枝。
- 双分支编码器分离几何与外观特征，避免信息失衡。
- 无需场景微调，仍保持高质量渲染且更省资源。
3D高斯溅射（3DGS）通过显式3D原语表示场景，实现了实时高保真新视角合成。然而，传统方法通常需要数百万个高斯点来捕捉复杂场景，导致内存和存储开销巨大。近期方法通过剪枝和场景特定参数微调减少模型规模，同时保持视觉质量，但通常依赖2D图像计算重要性分数并进行场景优化。本文提出PointSplat，一种结合高斯剪枝与变压器精炼的3D几何驱动框架。该方法包含两个核心组件：(1) 基于3D属性的高效剪枝策略，仅依靠3D特征排序高斯点，摆脱对2D图像的依赖；(2) 双分支编码器，分离并重新加权几何与外观特征，缓解特征不平衡问题。在ScanNet++和Replica数据集上，不同稀疏度下的大量实验表明，PointSplat在无需额外场景优化的情况下，持续实现具有竞争力的渲染质量与显著更高的效率。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has recently unlocked real-time, high-fidelity novel view synthesis by representing scenes using explicit 3D primitives. However, traditional methods often require millions of Gaussians to capture complex scenes, leading to significant memory and storage demands. Recent approaches have addressed this issue through pruning and per-scene fine-tuning of Gaussian parameters, thereby reducing the model size while maintaining visual quality. These strategies typically rely on 2D images to compute important scores followed by scene-specific optimization. In this work, we introduce PointSplat, 3D geometry-driven prune-and-refine framework that bridges previously disjoint directions of gaussian pruning and transformer refinement. Our method includes two key components: (1) an efficient geometry-driven strategy that ranks Gaussians based solely on their 3D attributes, removing reliance on 2D images during pruning stage, and (2) a dual-branch encoder that separates, re-weights geometric and appearance to avoid feature imbalance. Extensive experiments on ScanNet++ and Replica across varying sparsity levels demonstrate that PointSplat consistently achieves competitive rendering quality and superior efficiency without additional per-scene optimization.
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。