D-PLS: Decoupled Semantic Segmentation for 4D-Panoptic-LiDAR-Segmentation

TL;DR

This paper presents D-PLS, a decoupled approach for 4D Panoptic LiDAR Segmentation that improves instance and semantic segmentation by leveraging single-scan predictions and temporal aggregation, with broad compatibility and significant performance gains.

Contribution

D-PLS introduces a modular, decoupled framework for 4D Panoptic LiDAR Segmentation that enhances performance without requiring architectural changes or retraining.

Findings

Significant improvements in segmentation and tracking quality on SemanticKITTI.

Effective integration with existing semantic segmentation architectures.

Outperforms baseline methods in classification and association tasks.

Abstract

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.