Deep Magnification-Flexible Upsampling over 3D Point Clouds
Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Pages (from-to) | 8354-8367 |
Journal / Publication | IEEE Transactions on Image Processing |
Volume | 30 |
Online published | 30 Sep 2021 |
Publication status | Published - 2021 |
Link(s)
Abstract
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 predefined and fixed up sampling factor, the proposed framework only requires a single neural network with one-time training to handle various up sampling 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 athttps://github.com/ninaqy/Flexible-PU.
Research Area(s)
- Point cloud, sampling, linear approximation, deep learning, surface reconstruction
Citation Format(s)
Deep Magnification-Flexible Upsampling over 3D Point Clouds. / Qian, Yue; Hou, Junhui; Kwong, Sam; He, Ying.
In: IEEE Transactions on Image Processing, Vol. 30, 2021, p. 8354-8367.Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review