D-PLS: Decoupled Semantic Segmentation for 4D-Panoptic-LiDAR-Segmentation
This work addresses 4D panoptic segmentation for LiDAR data, which is important for autonomous driving applications, but it is incremental as it builds on existing semantic segmentation methods with a modular decoupling approach.
The paper tackles 4D panoptic LiDAR segmentation by decoupling semantic and instance segmentation, using single-scan semantic predictions as a prior for instance segmentation, and achieves significant improvements over the baseline on the SemanticKITTI dataset as measured by the LSTQ metric.
This paper introduces a novel approach to 4D Panoptic LiDAR Segmentation that decouples semantic and instance segmentation, leveraging single-scan semantic predictions as prior information for instance segmentation. Our method D-PLS first performs single-scan semantic segmentation and aggregates the results over time, using them to guide instance segmentation. The modular design of D-PLS allows for seamless integration on top of any semantic segmentation architecture, without requiring architectural changes or retraining. We evaluate our approach on the SemanticKITTI dataset, where it demonstrates significant improvements over the baseline in both classification and association tasks, as measured by the LiDAR Segmentation and Tracking Quality (LSTQ) metric. Furthermore, we show that our decoupled architecture not only enhances instance prediction but also surpasses the baseline due to advancements in single-scan semantic segmentation.