期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 30, 期 -, 页码 8354-8367出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2021.3115385
关键词
Three-dimensional displays; Geometry; Feature extraction; Training; Surface reconstruction; Image reconstruction; Deep learning; Point cloud; sampling; linear approximation; deep learning; surface reconstruction
资金
- Hong Kong Research Grants Council [CityU 11202320, CityU 11218121]
- Natural Science Foundation of China [61871342]
This paper proposes an end-to-end learning-based framework for generating dense point clouds from sparse ones, utilizing a lightweight neural network to adaptively learn interpolation weights and high-order refinements based on local geometry. The method is memory-efficient and flexible for various upsampling factors, showing superiority over existing methods in both quantitative and qualitative evaluations.
This paper addresses the problem of generating dense point clouds from given sparse point clouds to model the underlying geometric structures of objects/scenes. To tackle this challenging issue, we propose a novel end-to-end learning-based framework. Specifically, by taking advantage of the linear approximation theorem, we first formulate the problem explicitly, which boils down to determining the interpolation weights and high-order approximation errors. Then, we design a lightweight neural network to adaptively learn unified and sorted interpolation weights as well as the high-order refinements, by analyzing the local geometry of the input point cloud. The proposed method can be interpreted by the explicit formulation, and thus is more memory-efficient than existing ones. In sharp contrast to the existing methods that work only for a pre-defined and fixed upsampling factor, the proposed framework only requires a single neural network with one-time training to handle various upsampling factors within a typical range, which is highly desired in real-world applications. In addition, we propose a simple yet effective training strategy to drive such a flexible ability. In addition, our method can handle non-uniformly distributed and noisy data well. Extensive experiments on both synthetic and real-world data demonstrate the superiority of the proposed method over state-of-the-art methods both quantitatively and qualitatively. The code will be publicly available at https://github.com/ninaqy/Flexible-PU.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据