AdvectiveNet: An Eulerian-Lagrangian Fluidic reservoir for Point Cloud Processing

Abstract

This paper presents a novel physics-inspired deep learning approach for point cloud processing motivated by the natural flow phenomena in fluid mechanics. Our learning architecture jointly defines data in an Eulerian world space, using a static background grid, and a Lagrangian material space, using moving particles. By introducing this Eulerian-Lagrangian representation, we are able to naturally evolve and accumulate particle features using flow velocities generated from a generalized, high-dimensional force field. We demonstrate the efficacy of this system by solving various point cloud classification and segmentation problems with state-of-the-art performance. The entire geometric reservoir and data flow mimics the pipeline of the classic PIC/FLIP scheme in modeling natural flow, bridging the disciplines of geometric machine learning and physical simulation.

arXiv commentICLR 2020

References in corpus (9)

• Semi-Supervised Classification with Graph Convolutional Networks
• Geometric deep learning: going beyond Euclidean data
• Recent Advances in Physical Reservoir Computing: A Review
• PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation
• Point-Voxel CNN for Efficient 3D Deep Learning
• SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
• SPLATNet: Sparse Lattice Networks for Point Cloud Processing
• A Point Set Generation Network for 3D Object Reconstruction from a Single Image
• OctNet: Learning Deep 3D Representations at High Resolutions

Cited by in corpus (2)

• Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
• Learning to Reconstruct and Segment 3D Objects