# Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point Clouds

arXiv: https://arxiv.org/abs/1907.05279 · HTML: https://mlsanity.com/paper/1907.05279/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2019.

## Built on by (most cited first, 6 of 6)

- [A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction](https://mlsanity.com/paper/2211.14680/) (2022)
- [Offboard 3D Object Detection from Point Cloud Sequences](https://mlsanity.com/paper/2103.05073/) (2021)
- [PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences](https://mlsanity.com/paper/2205.13713/) (2022)
- [Learning Scene Dynamics from Point Cloud Sequences](https://mlsanity.com/paper/2111.08755/) (2021)
- [IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment](https://mlsanity.com/paper/2203.11590/) (2022)
- [Subspace Graph Physics: Real-Time Rigid Body-Driven Granular Flow Simulation](https://mlsanity.com/paper/2111.10206/) (2021)

## Abstract (arXiv)

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.