用学生t分布替代高斯，实现更优的3D渲染效果与参数效率
3D Student Splatting and Scooping
- 用灵活的学生t分布构建混合模型，支持正负密度表示
- 在多个数据集上实现与现有方法相当或更优的质量，组件数减少82%
- 提出新采样策略，解决新型模型的优化难题，适合神经渲染研究者
最近，3D高斯点阵（3DGS）为新视角合成提供了一种新框架，并在神经渲染及相关应用中掀起研究热潮。随着3DGS成为众多模型的基础组件，对其本身的改进将带来巨大收益。为此，我们旨在改进3DGS的根本范式与形式化表达。我们认为，作为非归一化混合模型，3DGS无需局限于高斯分布或点阵表示。因此，我们提出一种由灵活的学生t分布构成的新混合模型，支持正向（点阵）和负向（凹陷）密度。该模型命名为学生点阵与凹陷（SSS）。在提升表达能力的同时，SSS也带来了新的学习挑战。为此，我们还提出一种新的、基于原理的优化采样方法。通过在多个数据集、设置和指标上的全面评估与对比，我们证明了SSS在质量和参数效率方面均优于现有方法，例如在组件数量相近时达到匹配或更优质量，或在组件数减少高达82%的情况下仍获得可比结果。
原文摘要 · Abstract (English)
Recently, 3D Gaussian Splatting (3DGS) provides a new framework for novel view synthesis, and has spiked a new wave of research in neural rendering and related applications. As 3DGS is becoming a foundational component of many models, any improvement on 3DGS itself can bring huge benefits. To this end, we aim to improve the fundamental paradigm and formulation of 3DGS. We argue that as an unnormalized mixture model, it needs to be neither Gaussians nor splatting. We subsequently propose a new mixture model consisting of flexible Student's t distributions, with both positive (splatting) and negative (scooping) densities. We name our model Student Splatting and Scooping, or SSS. When providing better expressivity, SSS also poses new challenges in learning. Therefore, we also propose a new principled sampling approach for optimization. Through exhaustive evaluation and comparison, across multiple datasets, settings, and metrics, we demonstrate that SSS outperforms existing methods in terms of quality and parameter efficiency, e.g. achieving matching or better quality with similar numbers of components, and obtaining comparable results while reducing the component number by as much as 82%.
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。