主动选图提升高斯点云初始化效果，让3D渲染更清晰
ActiveInitSplat: How Active Image Selection Helps Gaussian Splatting
- 根据3D场景密度和占据情况动态选择视角图像
- 在真实与模拟场景中显著提升渲染质量，尤其在稀疏视角下
- 适合需要高质量3D重建的视觉项目开发者
高斯点云（GS）及其变体在实时场景渲染中表现优异，兼具低存储与高效计算优势。然而，初始训练阶段所选2D图像的质量对最终渲染效果影响重大。以往方法多采用被动、密集采样的方式选取图像，而本文提出「ActiveInitSplat」框架，通过分析已选图像生成的3D场景表示中的密度与占据度，主动选择覆盖更广视角的图像，使初始化的高斯函数更贴合实际3D结构。在多个知名仿真与真实环境上的实验表明，该方法在密集与稀疏视角设置下，均显著优于传统被动基线方法，在LPIPS、SSIM和PSNR等常用指标上实现明显提升。
原文摘要 · Abstract (English)
Gaussian splatting (GS) along with its extensions and variants provides outstanding performance in real-time scene rendering while meeting reduced storage demands and computational efficiency. While the selection of 2D images capturing the scene of interest is crucial for the proper initialization and training of GS, hence markedly affecting the rendering performance, prior works rely on passively and typically densely selected 2D images. In contrast, this paper proposes `ActiveInitSplat', a novel framework for active selection of training images for proper initialization and training of GS. ActiveInitSplat relies on density and occupancy criteria of the resultant 3D scene representation from the selected 2D images, to ensure that the latter are captured from diverse viewpoints leading to better scene coverage and that the initialized Gaussian functions are well aligned with the actual 3D structure. Numerical tests on well-known simulated and real environments demonstrate the merits of ActiveInitSplat resulting in significant GS rendering performance improvement over passive GS baselines in both dense- and sparse-view settings, in the widely adopted LPIPS, SSIM, and PSNR metrics.
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。