提前密集化：基于LiDAR的内容感知密集化以实现高效且高质量的3D高斯溅射
DensifyBeforehand: LiDAR-assisted Content-aware Densification for Efficient and Quality 3D Gaussian Splatting
AI总结：
本文提出基于LiDAR的内容感知密集化方法，通过结合稀疏LiDAR数据与单目深度估计，提升3D高斯溅射的初始化效率和视觉质量，降低资源消耗和训练时间。
摘要：
本文针对现有3D高斯溅射（3DGS）方法的局限性，特别是其依赖自适应密度控制，这可能导致漂浮伪影和资源使用效率低下。我们提出了一种新颖的提前密集化方法，通过结合稀疏LiDAR数据与对应的RGB图像单目深度估计，增强3D场景的初始化。我们的ROI感知采样方案优先考虑语义和几何上重要的区域，生成密集点云，从而提高视觉保真度和计算效率。这种提前密集化方法绕过了可能在原始流程中引入冗余高斯的自适应密度控制，使优化能够专注于3D高斯原始体的其他属性，减少重叠的同时提升视觉质量。我们的方法在与最先进技术相比时实现了相似的结果，同时显著降低了资源消耗和训练时间。我们通过在四个新收集的数据集上的广泛比较和消融研究验证了我们的方法，展示了其在复杂场景中保留感兴趣区域的有效性。
英文摘要：
This paper addresses the limitations of existing 3D Gaussian Splatting (3DGS) methods, particularly their reliance on adaptive density control, which can lead to floating artifacts and inefficient resource usage. We propose a novel densify beforehand approach that enhances the initialization of 3D scenes by combining sparse LiDAR data with monocular depth estimation from corresponding RGB images. Our ROI-aware sampling scheme prioritizes semantically and geometrically important regions, yielding a dense point cloud that improves visual fidelity and computational efficiency. This densify beforehand approach bypasses the adaptive density control that may introduce redundant Gaussians in the original pipeline, allowing the optimization to focus on the other attributes of 3D Gaussian primitives, reducing overlap while enhancing visual quality. Our method achieves comparable results to state-of-the-art techniques while significantly lowering resource consumption and training time. We validate our approach through extensive comparisons and ablation studies on four newly collected datasets, showcasing its effectiveness in preserving regions of interest in complex scenes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
