Abstract Flow for Temporal Semantic Segmentation on the Permutohedral Lattice
This work addresses the need for temporal semantic segmentation in autonomous agents, offering an incremental improvement by integrating temporal processing into an existing backbone.
The authors tackled the problem of distinguishing moving objects and leveraging temporal information in semantic segmentation by extending LatticeNet to process temporal point cloud data and introducing an Abstract Flow module for matching similar abstract features across time, achieving state-of-the-art results on the SemanticKITTI dataset.
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 .