Point Cloud Upsampling through Patch-based Frequency Superposition
For point cloud processing tasks, this work provides a training-free, interpretable alternative to neural network methods, achieving superior geometric accuracy.
PUtPFS is an optimization-based point cloud upsampling method that uses patch-based frequency superposition to estimate surfaces and place new points, achieving the best point-to-surface distance among all methods and the best Chamfer/Hausdorff distances among optimization-based approaches, without requiring training data.
In recent years, neural networks have become the dominant models in most point cloud upsampling methods. Although these approaches are achieving good results, they do have drawbacks, such as a lack of interpretability and data dependency. Moreover, they have to be trained on a dataset that is similar to the test data in order to perform well. To avoid these disadvantages, we propose Point Cloud Upsampling through Patch-based Frequency Superposition (PUtPFS), an optimization-based approach that selects subsets of points and estimates the surface of this set through superpositioning spatial frequencies. Then, new points are placed on this surface. By successively selecting points in the least dense regions of the point cloud, a uniform upsampling can be reached. With this method, we surpass the current best upsampling results in the commonly considered point-to-surface distance. Furthermore, we achieve the best Chamfer and Hausdorff distance among the optimization-based approaches. As an additional advantage, our method does not need any training data and is mathematically interpretable.