论文标题
任意点云与高斯球面混合物进行更新
Arbitrary Point Cloud Upsampling with Spherical Mixture of Gaussians
论文作者
论文摘要
从稀疏的原始数据中生成密集的点云使下游3D理解任务，但现有模型仅限于固定的上采样率或短范围的整数值。在本文中，我们提出了APU-SMOG，这是一种基于变压器的模型，用于任意点云上采样（APU）。首先将稀疏输入映射到高斯（烟雾）分布的球形混合物，从中可以采样任意数量的点。然后，将这些样品作为查询馈送到变压器解码器，将它们映射回目标表面。广泛的定性和定量评估表明，APU-SMOG的表现优于最先进的固定比率方法，同时使用任何训练有素的模型有效地使用任何缩放系数（包括非直觉值）来提高采样。该代码可从https://github.com/apusmog/apusmog/获得
Generating dense point clouds from sparse raw data benefits downstream 3D understanding tasks, but existing models are limited to a fixed upsampling ratio or to a short range of integer values. In this paper, we present APU-SMOG, a Transformer-based model for Arbitrary Point cloud Upsampling (APU). The sparse input is firstly mapped to a Spherical Mixture of Gaussians (SMOG) distribution, from which an arbitrary number of points can be sampled. Then, these samples are fed as queries to the Transformer decoder, which maps them back to the target surface. Extensive qualitative and quantitative evaluations show that APU-SMOG outperforms state-of-the-art fixed-ratio methods, while effectively enabling upsampling with any scaling factor, including non-integer values, with a single trained model. The code is available at https://github.com/apusmog/apusmog/
