Leveraging 3D Representation Alignment and RGB Pretrained Priors for LiDAR Scene Generation

• URL: http://arxiv.org/abs/2601.07692v1
• Date: Mon, 12 Jan 2026 16:20:20 GMT
• Title: Leveraging 3D Representation Alignment and RGB Pretrained Priors for LiDAR Scene Generation
• Authors: Nicolas Sereyjol-Garros, Ellington Kirby, Victor Besnier, Nermin Samet,
• Abstract summary: We introduce R3DPA, the first LiDAR scene generation method to unlock image-pretrained priors for LiDAR point clouds.<n>Specifically, we (i) align intermediate features of our generative model with self-supervised 3D features, which substantially improves generation quality.<n>We also enable point cloud control at inference for object inpainting and scene mixing with solely an unconditional model.
• Score: 7.970454839582266
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LiDAR scene synthesis is an emerging solution to scarcity in 3D data for robotic tasks such as autonomous driving. Recent approaches employ diffusion or flow matching models to generate realistic scenes, but 3D data remains limited compared to RGB datasets with millions of samples. We introduce R3DPA, the first LiDAR scene generation method to unlock image-pretrained priors for LiDAR point clouds, and leverage self-supervised 3D representations for state-of-the-art results. Specifically, we (i) align intermediate features of our generative model with self-supervised 3D features, which substantially improves generation quality; (ii) transfer knowledge from large-scale image-pretrained generative models to LiDAR generation, mitigating limited LiDAR datasets; and (iii) enable point cloud control at inference for object inpainting and scene mixing with solely an unconditional model. On the KITTI-360 benchmark R3DPA achieves state of the art performance. Code and pretrained models are available at https://github.com/valeoai/R3DPA.

Related papers

• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models [67.50989119438508]
  We introduce DSplats, a novel method that directly denoises multiview images using Gaussian-based Reconstructors to produce realistic 3D assets.<n>Our experiments demonstrate that DSplats not only produces high-quality, spatially consistent outputs, but also sets a new standard in single-image to 3D reconstruction.
  arXiv  Detail & Related papers  (2024-12-11T07:32:17Z)
• Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection [52.66283064389691]
  State-of-the-art 3D object detectors are often trained on massive labeled datasets. Recent works demonstrate that self-supervised pre-training with unlabeled data can improve detection accuracy with limited labels. We propose a shelf-supervised approach for generating zero-shot 3D bounding boxes from paired RGB and LiDAR data.
  arXiv  Detail & Related papers  (2024-06-14T15:21:57Z)
• DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data [50.164670363633704]
  We present DIRECT-3D, a diffusion-based 3D generative model for creating high-quality 3D assets from text prompts. Our model is directly trained on extensive noisy and unaligned in-the-wild' 3D assets. We achieve state-of-the-art performance in both single-class generation and text-to-3D generation.
  arXiv  Detail & Related papers  (2024-06-06T17:58:15Z)
• SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior [53.52396082006044]
  Current methods struggle to maintain rendering quality at the viewpoint that deviates significantly from the training viewpoints. This issue stems from the sparse training views captured by a fixed camera on a moving vehicle. We propose a novel approach that enhances the capacity of 3DGS by leveraging prior from a Diffusion Model.
  arXiv  Detail & Related papers  (2024-03-29T09:20:29Z)
• 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)
• NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields [20.887421720818892]
  We present NeRF-LIDAR, a novel LiDAR simulation method that leverages real-world information to generate realistic LIDAR point clouds. We verify the effectiveness of our NeRF-LiDAR by training different 3D segmentation models on the generated LiDAR point clouds.
  arXiv  Detail & Related papers  (2023-04-28T12:41:28Z)
• NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions [97.27105725738016]
  integration of Neural Radiance Fields (NeRFs) and generative models, such as Generative Adversarial Networks (GANs) has transformed 3D-aware generation from single-view images. We propose a simple and effective method, based on re-using the well-disentangled latent space of a pre-trained NeRF-GAN in a pose-conditioned convolutional network to directly generate 3D-consistent images corresponding to the underlying 3D representations.
  arXiv  Detail & Related papers  (2023-03-22T18:59:48Z)

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.