Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point Clouds
This work addresses stability issues in point cloud processing for applications like computer graphics and simulation, representing an incremental improvement with a specific technical contribution.
The paper tackles the problem of flickering and halo artifacts in learning temporally coherent features for deforming point clouds by introducing a novel temporal loss function that considers higher time derivatives, and demonstrates its effectiveness on large, deforming point sets from various sources.
Point clouds, as a form of Lagrangian representation, allow for powerful and flexible applications in a large number of computational disciplines. We propose a novel deep-learning method to learn stable and temporally coherent feature spaces for points clouds that change over time. We identify a set of inherent problems with these approaches: without knowledge of the time dimension, the inferred solutions can exhibit strong flickering, and easy solutions to suppress this flickering can result in undesirable local minima that manifest themselves as halo structures. We propose a novel temporal loss function that takes into account higher time derivatives of the point positions, and encourages mingling, i.e., to prevent the aforementioned halos. We combine these techniques in a super-resolution method with a truncation approach to flexibly adapt the size of the generated positions. We show that our method works for large, deforming point sets from different sources to demonstrate the flexibility of our approach.