用频域叠加方法无训练提升点云上采样质量
Point Cloud Upsampling through Patch-based Frequency Superposition
- 基于局部块的频域叠加重构表面，动态选择稀疏区域增点
- 在点到面距离上超越现有最优结果，Chamfer与Hausdorff距离领先优化类方法
- 无需训练数据，数学可解释，适合对可靠性要求高的场景
近年来，神经网络已成为多数点云上采样的主流模型，尽管性能良好，但仍存在可解释性差、依赖训练数据等问题，需在与测试数据相似的数据集上训练才能表现优异。为克服这些缺陷，本文提出基于局部块频域叠加的点云上采样方法（PUtPFS），通过选取点集子集并利用空间频率叠加估计其表面，再在该表面上生成新点。通过不断选择点云中密度最低区域进行增点，实现均匀上采样。该方法在常见点到面距离指标上超越当前最优结果，并在优化类方法中取得最佳的Chamfer距离与Hausdorff距离。此外，本方法无需任何训练数据，具有数学可解释性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。