Is clustering enough for LiDAR instance segmentation? A state-of-the-art training-free baseline
This addresses the high cost of manual annotations for autonomous driving scene understanding, offering a training-free and efficient solution.
The paper tackles LiDAR panoptic segmentation by showing that competitive performance can be achieved using only semantic labels without training or instance annotations, outperforming most supervised methods on benchmarks like SemanticKITTI and nuScenes while running in real-time on a CPU.
Panoptic segmentation of LiDAR point clouds is fundamental to outdoor scene understanding, with autonomous driving being a primary application. While state-of-the-art approaches typically rely on end-to-end deep learning architectures and extensive manual annotations of instances, the significant cost and time investment required for labeling large-scale point cloud datasets remains a major bottleneck in this field. In this work, we demonstrate that competitive panoptic segmentation can be achieved using only semantic labels, with instances predicted without any training or annotations. Our method outperforms {most} state-of-the-art supervised methods on standard benchmarks including SemanticKITTI and nuScenes, and outperforms every publicly available method on SemanticKITTI as a drop-in instance head replacement, while running in real-time on a single-threaded CPU and requiring no instance labels. It is fully explainable, and requires no learning or parameter tuning. Alpine combined with state-of-the-art semantic segmentation ranks first on the official panoptic segmentation leaderboard of SemanticKITTI. Code is available at https://github.com/valeoai/Alpine/