Spiral: Semantic-Aware Progressive LiDAR Scene Generation and Understanding

Dekai Zhu*     Yixuan Hu*     Youquan Liu     Dongyue Lu     Lingdong Kong     Slobodan Ilic
(* Equal Contribution)
NeurIPS 2025

Existing LiDAR generative models are limited to producing unlabeled LiDAR scenes, lacking any semantic annotations. Performing post-hoc labeling on these generated scenes requires additional pretrained segmentation models, which introduces extra computational overhead. Moreover, such after-the-fact annotation yields suboptimal segmentation quality.

To address this issue, we make the following contributions:

• We propose a novel state-of-the-art semantic-aware range-view LiDAR diffusion model, Spiral, which jointly produces depth and reflectance images along with semantic labels.
• We introduce unified evaluation metrics that comprehensively evaluate the geometric, physical, and semantic quality of generated labeled LiDAR scenes.
• We demonstrate the effectiveness of the generated LiDAR scenes for training segmentation models, highlighting Spiral's potential for generative data augmentation.

:books: Citation

If you find this work helpful for your research, please kindly consider citing our paper:

@inproceedings{zhu2025spiral,
    title     = {Spiral: Semantic-Aware Progressive LiDAR Scene Generation and Understanding},
    author    = {Zhu, Dekai and Hu, Yixuan and Liu, Youquan and Lu, Dongyue and Kong, Lingdong and Ilic, Slobodan},
    booktitle = {The Thirty-ninth Annual Conference on Neural Information Processing Systems},
    year      = {2025}
}

Updates

• [11/2025] - The code for Spiral is released. :rocket:
• [10/2025] - The project page is online. :rocket:
• [09/2025] - This work has been accepted to NeurIPS 2025.

:gear: Installation

For details related to installation and environment setups, please run:

conda env create -f environment.yaml
conda activate spiral

If you are stuck with an endless installation, try:

mamba env create -f environment.yaml
conda activate spiral

:hotsprings: Data Preparation

We use the official SemanticKITTI API to preprocess the data by projecting the LiDAR data from Cartesian coordinates into range images. You can download the preprocessed data here. :hugs:

:rocket: Getting Started

First, specify the data_path in utils/option.py to point to the directory of the preprocessed data. Then simply run:

python train.py

to start the training.

Acknowledgements

This work is developed based on the R2DM codebase.