针对大场景重建中点云稀疏导致的渲染失真问题，提出信号结构感知调度器提升重建效率与质量。
Signal Structure-Aware Gaussian Splatting for Large-Scale Scene Reconstruction
- 基于信号结构恢复视角，动态调节图像分辨率与高斯点密度以匹配场景频率收敛
- 在LargeScaleNeRF数据集上实现4.3倍加速，渲染质量提升2.1倍PSNR
- 适合需要高效高保真重建的大场景3D应用，如城市级数字孪生
3D高斯溅射在新视角合成中展现出巨大潜力。然而，在大规模场景中，不可避免地存在观测稀疏区域，初始点云过于稀疏。此时，用高频图像监督由低频稀疏点初始化的高斯点，常引发不可控的密集化和冗余原型，降低效率与质量。直观上可通过调度策略缓解，分为两类：通过密集化调节目标信号频率，或通过图像分辨率调节采样频率。但现有调度策略多为硬编码，无法感知场景频率的收敛行为。为此，我们从信号结构恢复角度重新审视场景重建问题，提出SIG调度器，使图像监督与高斯频率同步。具体而言，推导3D表示的平均采样频率与带宽，并据此调控训练图像分辨率与高斯密集化过程。此外，引入球约束高斯点，利用初始点云的空间先验控制高斯优化。本框架实现频率一致、几何感知且无漂浮物的训练，在大规模场景中显著优于现有方法，效率与渲染质量均达顶尖水平。代码已公开于https://github.com/weiyixue999/Signal_Structure_Aware_Gaussian。
原文摘要 · Abstract (English)
3D Gaussian Splatting has demonstrated remarkable potential in novel view synthesis. In contrast to small-scale scenes, large-scale scenes inevitably contain sparsely observed regions with excessively sparse initial points. In this case, supervising Gaussians initialized from low-frequency sparse points with high-frequency images often induces uncontrolled densification and redundant primitives, degrading both efficiency and quality. Intuitively, this issue can be mitigated with scheduling strategies, which can be categorized into two paradigms: modulating target signal frequency via densification and modulating sampling frequency via image resolution. However, previous scheduling strategies are primarily hardcoded, failing to perceive the convergence behavior of scene frequency. To address this, we reframe the scene reconstruction problem from the perspective of signal structure recovery and propose SIG, a novel scheduler that synchronizes image supervision with Gaussian frequencies. Specifically, we derive the average sampling frequency and bandwidth of 3D representations, and then regulate the training image resolution and the Gaussian densification process based on scene frequency convergence. Furthermore, we introduce Sphere-Constrained Gaussians, which leverage the spatial prior of initialized point clouds to control Gaussian optimization. Our framework enables frequency-consistent, geometry-aware, and floater-free training, achieving state-of-the-art performance by a substantial margin in both efficiency and rendering quality in large-scale scenes. The code is available at: https://github.com/weiyixue999/Signal_Structure_Aware_Gaussian
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。