GaussianGrow：基于文本引导从3D点云几何感知地生长高斯
GaussianGrow: Geometry-aware Gaussian Growing from 3D Point Clouds with Text Guidance
提出从点云生长高斯的框架，利用多视图扩散模型合成一致外观监督，并通过迭代检测未生长区域和2D扩散修复补全，为文本引导的3D高斯生成提供了几何准确的方案。
原文依据 we introduce GaussianGrow, a novel approach that generates 3D Gaussians by learning to grow them from easily accessible 3D point clouds
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论3D高斯泼溅在渲染效率和质量上表现出优越性能，但在缺乏适当几何先验的情况下，3D高斯的生成仍然是一个挑战。现有方法探索了预测点图作为几何参考来推断高斯基元，然而不可靠的估计几何可能导致生成效果不佳。在本工作中，我们引入了GaussianGrow，一种通过从易于获取的3D点云学习生长3D高斯的新方法，自然地在高斯生成中强制几何准确性。具体而言，我们设计了一种文本引导的高斯生长方案，利用多视图扩散模型从输入点云合成一致的外观以进行监督。为了减轻融合相邻视图造成的伪影，我们约束在非预设相机姿态下生成的新视图，这些姿态在不同视图的重叠区域中被识别。为了补全难以观察的区域，我们提出通过观察点云中最大的未生长区域来迭代检测相机姿态，并使用预训练的2D扩散模型对渲染视图进行图像修复来补全它们。该过程持续直到生成完整的高斯。我们在合成甚至真实扫描的点云上对文本引导的高斯生成进行了广泛评估。
英文原文摘要 1376 字符
3D Gaussian Splatting has demonstrated superior performance in rendering efficiency and quality, yet the generation of 3D Gaussians still remains a challenge without proper geometric priors. Existing methods have explored predicting point maps as geometric references for inferring Gaussian primitives, while the unreliable estimated geometries may lead to poor generations. In this work, we introduce GaussianGrow, a novel approach that generates 3D Gaussians by learning to grow them from easily accessible 3D point clouds, naturally enforcing geometric accuracy in Gaussian generation. Specifically, we design a text-guided Gaussian growing scheme that leverages a multi-view diffusion model to synthesize consistent appearances from input point clouds for supervision. To mitigate artifacts caused by fusing neighboring views, we constrain novel views generated at non-preset camera poses identified in overlapping regions across different views. For completing the hard-to-observe regions, we propose to iteratively detect the camera pose by observing the largest un-grown regions in point clouds and inpainting them by inpainting the rendered view with a pretrained 2D diffusion model. The process continues until complete Gaussians are generated. We extensively evaluate GaussianGrow on text-guided Gaussian generation from synthetic and even real-scanned point clouds.