SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding

TL;DR

Spiral is a novel range-view LiDAR diffusion model that generates depth, reflectance, and semantic maps simultaneously, improving scene generation quality and aiding data augmentation for segmentation tasks.

Contribution

It introduces a semantic-aware diffusion model for range-view LiDAR data, enhancing generation quality and reducing labeling effort compared to existing methods.

Findings

Achieves state-of-the-art performance on SemanticKITTI and nuScenes datasets.

Uses fewer parameters than existing models.

Effectively improves downstream segmentation training through synthetic data augmentation.

Abstract

Leveraging recent diffusion models, LiDAR-based large-scale 3D scene generation has achieved great success. While recent voxel-based approaches can generate both geometric structures and semantic labels, existing range-view methods are limited to producing unlabeled LiDAR scenes. Relying on pretrained segmentation models to predict the semantic maps often results in suboptimal cross-modal consistency. To address this limitation while preserving the advantages of range-view representations, such as computational efficiency and simplified network design, we propose Spiral, a novel range-view LiDAR diffusion model that simultaneously generates depth, reflectance images, and semantic maps. Furthermore, we introduce novel semantic-aware metrics to evaluate the quality of the generated labeled range-view data. Experiments on the SemanticKITTI and nuScenes datasets demonstrate that Spiral achieves state-of-the-art performance with the smallest parameter size, outperforming two-step methods that combine the generative and segmentation models. Additionally, we validate that range images generated by Spiral can be effectively used for synthetic data augmentation in the downstream segmentation training, significantly reducing the labeling effort on LiDAR data.