CVFeb 1, 2020

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

arXiv:2002.00118v37 citations
AI Analysis

This addresses point cloud analysis for applications like computer vision and robotics, representing a novel method for a known bottleneck.

The paper tackled point cloud processing by introducing a physics-inspired deep learning approach based on fluid mechanics, achieving state-of-the-art performance in classification and segmentation tasks.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes