Parametric Surface Constrained Upsampler Network for Point Cloud
This addresses the issue of outlier points in point cloud processing for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of generating clean, dense point clouds from sparse inputs by introducing a surface regularizer that constrains generated points to an underlying parametric surface, achieving state-of-the-art results in point cloud upsampling and completion tasks.
Designing a point cloud upsampler, which aims to generate a clean and dense point cloud given a sparse point representation, is a fundamental and challenging problem in computer vision. A line of attempts achieves this goal by establishing a point-to-point mapping function via deep neural networks. However, these approaches are prone to produce outlier points due to the lack of explicit surface-level constraints. To solve this problem, we introduce a novel surface regularizer into the upsampler network by forcing the neural network to learn the underlying parametric surface represented by bicubic functions and rotation functions, where the new generated points are then constrained on the underlying surface. These designs are integrated into two different networks for two tasks that take advantages of upsampling layers - point cloud upsampling and point cloud completion for evaluation. The state-of-the-art experimental results on both tasks demonstrate the effectiveness of the proposed method. The code is available at https://github.com/corecai163/PSCU.