Volumetric Semantically Consistent 3D Panoptic Mapping
This work addresses the need for comprehensive semantic 3D mapping for autonomous agents in unstructured environments, though it appears to be an incremental improvement over existing Voxel-TSDF approaches.
The authors developed an online 2D-to-3D semantic instance mapping algorithm that generates accurate 3D maps for autonomous agents, achieving state-of-the-art accuracy on public datasets with improvements across multiple metrics. They also identified a critical evaluation flaw in recent studies where using ground truth trajectories instead of SLAM-estimated ones creates a large performance gap on real-world data.
We introduce an online 2D-to-3D semantic instance mapping algorithm aimed at generating comprehensive, accurate, and efficient semantic 3D maps suitable for autonomous agents in unstructured environments. The proposed approach is based on a Voxel-TSDF representation used in recent algorithms. It introduces novel ways of integrating semantic prediction confidence during mapping, producing semantic and instance-consistent 3D regions. Further improvements are achieved by graph optimization-based semantic labeling and instance refinement. The proposed method achieves accuracy superior to the state of the art on public large-scale datasets, improving on a number of widely used metrics. We also highlight a downfall in the evaluation of recent studies: using the ground truth trajectory as input instead of a SLAM-estimated one substantially affects the accuracy, creating a large gap between the reported results and the actual performance on real-world data.