TopoLiDM: Topology-Aware LiDAR Diffusion Models for Interpretable and Realistic LiDAR Point Cloud Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Jiuming, Huang, Zheng, Liu, Mengmeng, Deng, Tianchen, Nex, Francesco, Cheng, Hao, Wang, Hesheng
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913965949321216
author Liu, Jiuming
Huang, Zheng
Liu, Mengmeng
Deng, Tianchen
Nex, Francesco
Cheng, Hao
Wang, Hesheng
author_facet Liu, Jiuming
Huang, Zheng
Liu, Mengmeng
Deng, Tianchen
Nex, Francesco
Cheng, Hao
Wang, Hesheng
contents LiDAR scene generation is critical for mitigating real-world LiDAR data collection costs and enhancing the robustness of downstream perception tasks in autonomous driving. However, existing methods commonly struggle to capture geometric realism and global topological consistency. Recent LiDAR Diffusion Models (LiDMs) predominantly embed LiDAR points into the latent space for improved generation efficiency, which limits their interpretable ability to model detailed geometric structures and preserve global topological consistency. To address these challenges, we propose TopoLiDM, a novel framework that integrates graph neural networks (GNNs) with diffusion models under topological regularization for high-fidelity LiDAR generation. Our approach first trains a topological-preserving VAE to extract latent graph representations by graph construction and multiple graph convolutional layers. Then we freeze the VAE and generate novel latent topological graphs through the latent diffusion models. We also introduce 0-dimensional persistent homology (PH) constraints, ensuring the generated LiDAR scenes adhere to real-world global topological structures. Extensive experiments on the KITTI-360 dataset demonstrate TopoLiDM's superiority over state-of-the-art methods, achieving improvements of 22.6% lower Frechet Range Image Distance (FRID) and 9.2% lower Minimum Matching Distance (MMD). Notably, our model also enables fast generation speed with an average inference time of 1.68 samples/s, showcasing its scalability for real-world applications. We will release the related codes at https://github.com/IRMVLab/TopoLiDM.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22454
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TopoLiDM: Topology-Aware LiDAR Diffusion Models for Interpretable and Realistic LiDAR Point Cloud Generation
Liu, Jiuming
Huang, Zheng
Liu, Mengmeng
Deng, Tianchen
Nex, Francesco
Cheng, Hao
Wang, Hesheng
Computer Vision and Pattern Recognition
Image and Video Processing
LiDAR scene generation is critical for mitigating real-world LiDAR data collection costs and enhancing the robustness of downstream perception tasks in autonomous driving. However, existing methods commonly struggle to capture geometric realism and global topological consistency. Recent LiDAR Diffusion Models (LiDMs) predominantly embed LiDAR points into the latent space for improved generation efficiency, which limits their interpretable ability to model detailed geometric structures and preserve global topological consistency. To address these challenges, we propose TopoLiDM, a novel framework that integrates graph neural networks (GNNs) with diffusion models under topological regularization for high-fidelity LiDAR generation. Our approach first trains a topological-preserving VAE to extract latent graph representations by graph construction and multiple graph convolutional layers. Then we freeze the VAE and generate novel latent topological graphs through the latent diffusion models. We also introduce 0-dimensional persistent homology (PH) constraints, ensuring the generated LiDAR scenes adhere to real-world global topological structures. Extensive experiments on the KITTI-360 dataset demonstrate TopoLiDM's superiority over state-of-the-art methods, achieving improvements of 22.6% lower Frechet Range Image Distance (FRID) and 9.2% lower Minimum Matching Distance (MMD). Notably, our model also enables fast generation speed with an average inference time of 1.68 samples/s, showcasing its scalability for real-world applications. We will release the related codes at https://github.com/IRMVLab/TopoLiDM.
title TopoLiDM: Topology-Aware LiDAR Diffusion Models for Interpretable and Realistic LiDAR Point Cloud Generation
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2507.22454