Abstract Flow for Temporal Semantic Segmentation on the Permutohedral Lattice

TL;DR

This paper introduces Abstract Flow, a novel module for temporal semantic segmentation on point clouds, extending LatticeNet to incorporate temporal information and achieve state-of-the-art results on SemanticKITTI.

Contribution

It proposes Abstract Flow, a new module inspired by optical flow, enabling temporal feature matching in point cloud segmentation.

Findings

Achieves state-of-the-art results on SemanticKITTI dataset.

Extends LatticeNet to process temporal point cloud data.

Provides open-source implementation in PyTorch.

Abstract

Semantic segmentation is a core ability required by autonomous agents, as being able to distinguish which parts of the scene belong to which object class is crucial for navigation and interaction with the environment. Approaches which use only one time-step of data cannot distinguish between moving objects nor can they benefit from temporal integration. In this work, we extend a backbone LatticeNet to process temporal point cloud data. Additionally, we take inspiration from optical flow methods and propose a new module called Abstract Flow which allows the network to match parts of the scene with similar abstract features and gather the information temporally. We obtain state-of-the-art results on the SemanticKITTI dataset that contains LiDAR scans from real urban environments. We share the PyTorch implementation of TemporalLatticeNet at https://github.com/AIS-Bonn/temporal_latticenet .