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

• URL: http://arxiv.org/abs/2507.22454v1
• Date: Wed, 30 Jul 2025 08:02:42 GMT
• Title: TopoLiDM: Topology-Aware LiDAR Diffusion Models for Interpretable and Realistic LiDAR Point Cloud Generation
• Authors: Jiuming Liu, Zheng Huang, Mengmeng Liu, Tianchen Deng, Francesco Nex, Hao Cheng, Hesheng Wang,
• Abstract summary: TopoLiDM is a novel framework that integrates graph neural networks with diffusion models under topological regularization for high-fidelity LiDAR generation.<n>Our approach first trains a topological-preserving VAE to extract latent graph representations by graph construction and multiple graph convolutional layers.<n>Extensive experiments on the KITTI-360 dataset demonstrate TopoLiDM's superiority over state-of-the-art methods.
• Score: 15.223634903890863
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation [10.77777607732642]
  Spiral is a novel range-view LiDAR diffusion model that simultaneously generates depth, reflectance images, and semantic maps.<n> Experiments on the Semantic KITTI and nuScenes datasets demonstrate that Spiral achieves state-of-the-art performance with the smallest parameter size.
  arXiv  Detail & Related papers  (2025-05-28T17:55:35Z)
• Enhancing Steering Estimation with Semantic-Aware GNNs [41.89219383258699]
  hybrid architectures combine 3D neural network models with recurrent neural networks (RNNs) for temporal modeling.<n>We evaluate four hybrid 3D models, all of which outperform the 2D-only baseline.<n>We validate our approach on the KITTI dataset, achieving a 71% improvement over 2D-only models.
  arXiv  Detail & Related papers  (2025-03-21T13:58:08Z)
• SeaDAG: Semi-autoregressive Diffusion for Conditional Directed Acyclic Graph Generation [83.52157311471693]
  We introduce SeaDAG, a semi-autoregressive diffusion model for conditional generation of Directed Acyclic Graphs (DAGs) Unlike conventional autoregressive generation that lacks a global graph structure view, our method maintains a complete graph structure at each diffusion step. We explicitly train the model to learn graph conditioning with a condition loss, which enhances the diffusion model's capacity to generate realistic DAGs.
  arXiv  Detail & Related papers  (2024-10-21T15:47:03Z)
• LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splatting [50.808933338389686]
  We present LiDAR-GS, a real-time, high-fidelity re-simulation of LiDAR scans in public urban road scenes.<n>The method achieves state-of-the-art results in both rendering frame rate and quality on publically available large scene datasets.
  arXiv  Detail & Related papers  (2024-10-07T15:07:56Z)
• RangeLDM: Fast Realistic LiDAR Point Cloud Generation [12.868053836790194]
  We introduce RangeLDM, a novel approach for rapidly generating high-quality range-view LiDAR point clouds. We achieve this by correcting range-view data distribution for accurate projection from point clouds to range images via Hough voting. We instruct the model to preserve 3D structural fidelity by devising a range-guided discriminator.
  arXiv  Detail & Related papers  (2024-03-15T08:19:57Z)
• LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment [59.320414108383055]
  We present LiveHPS, a novel single-LiDAR-based approach for scene-level human pose and shape estimation. We propose a huge human motion dataset, named FreeMotion, which is collected in various scenarios with diverse human poses.
  arXiv  Detail & Related papers  (2024-02-27T03:08:44Z)
• LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models [1.1965844936801797]
  Generative modeling of 3D LiDAR data is an emerging task with promising applications for autonomous mobile robots. We present R2DM, a novel generative model for LiDAR data that can generate diverse and high-fidelity 3D scene point clouds. Our method is built upon denoising diffusion probabilistic models (DDPMs), which have shown impressive results among generative model frameworks.
  arXiv  Detail & Related papers  (2023-09-17T12:26:57Z)
• SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases [66.61789780666727]
  We show how the second-order continuity can be incorporated into GNNs while maintaining the equivariant property. We also offer theoretical insights into SEGNO, highlighting that it can learn a unique trajectory between adjacent states. Our model yields a significant improvement over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-08-25T07:15:58Z)
• LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields [112.62936571539232]
  We introduce a new task, novel view synthesis for LiDAR sensors. Traditional model-based LiDAR simulators with style-transfer neural networks can be applied to render novel views. We use a neural radiance field (NeRF) to facilitate the joint learning of geometry and the attributes of 3D points.
  arXiv  Detail & Related papers  (2023-04-20T15:44:37Z)
• GELATO: Geometrically Enriched Latent Model for Offline Reinforcement Learning [54.291331971813364]
  offline reinforcement learning approaches can be divided into proximal and uncertainty-aware methods. In this work, we demonstrate the benefit of combining the two in a latent variational model. Our proposed metrics measure both the quality of out of distribution samples as well as the discrepancy of examples in the data.
  arXiv  Detail & Related papers  (2021-02-22T19:42:40Z)
• SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks [81.64530401885476]
  We propose a self-supervised LiDAR odometry method, dubbed SelfVoxeLO, to tackle these two difficulties. Specifically, we propose a 3D convolution network to process the raw LiDAR data directly, which extracts features that better encode the 3D geometric patterns. We evaluate our method's performances on two large-scale datasets, i.e., KITTI and Apollo-SouthBay.
  arXiv  Detail & Related papers  (2020-10-19T09:23:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.