Physically Based Neural LiDAR Resimulation

• URL: http://arxiv.org/abs/2507.12489v1
• Date: Tue, 15 Jul 2025 19:49:44 GMT
• Title: Physically Based Neural LiDAR Resimulation
• Authors: Richard Marcus, Marc Stamminger,
• Abstract summary: We show that our method achieves more accurate LiDAR simulation compared to existing techniques.<n>Our approach exhibits advanced resimulation capabilities, such as generating high resolution LiDAR scans in the camera perspective.
• Score: 4.349248791803596
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Methods for Novel View Synthesis (NVS) have recently found traction in the field of LiDAR simulation and large-scale 3D scene reconstruction. While solutions for faster rendering or handling dynamic scenes have been proposed, LiDAR specific effects remain insufficiently addressed. By explicitly modeling sensor characteristics such as rolling shutter, laser power variations, and intensity falloff, our method achieves more accurate LiDAR simulation compared to existing techniques. We demonstrate the effectiveness of our approach through quantitative and qualitative comparisons with state-of-the-art methods, as well as ablation studies that highlight the importance of each sensor model component. Beyond that, we show that our approach exhibits advanced resimulation capabilities, such as generating high resolution LiDAR scans in the camera perspective. Our code and the resulting dataset are available at https://github.com/richardmarcus/PBNLiDAR.

Related papers

• GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting [3.376357029373187]
  GS-LiDAR is a novel framework for generating realistic LiDAR point clouds with panoramic Gaussian splatting.<n>We introduce a novel panoramic rendering technique with explicit ray-splat intersection, guided by panoramic LiDAR supervision.
  arXiv  Detail & Related papers  (2025-01-22T11:21:20Z)
• LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation [31.79143254487969]
  LiDAR-RT is a novel framework that supports real-time, physically accurate LiDAR re-simulation for driving scenes.<n>Our primary contribution is the development of an efficient and effective rendering pipeline.<n>Our framework supports realistic rendering with flexible scene editing operations and various sensor configurations.
  arXiv  Detail & Related papers  (2024-12-19T18:58:36Z)
• Gait Sequence Upsampling using Diffusion Models for Single LiDAR Sensors [1.0485739694839664]
  LidarGSU is designed to improve the generalization capability of existing identification models. In this work, we leverage DPMs on sparse sequential pedestrian point clouds as conditional masks in a video-to-video translation approach. We conduct extensive experiments on the SUSTeck1K dataset to evaluate the generative quality and recognition performance of the proposed method.
  arXiv  Detail & Related papers  (2024-10-11T10:11:21Z)
• 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)
• 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)
• Neural LiDAR Fields for Novel View Synthesis [80.45307792404685]
  We present Neural Fields for LiDAR (NFL), a method to optimise a neural field scene representation from LiDAR measurements. NFL combines the rendering power of neural fields with a detailed, physically motivated model of the LiDAR sensing process. We show that the improved realism of the synthesized views narrows the domain gap to real scans and translates to better registration and semantic segmentation performance.
  arXiv  Detail & Related papers  (2023-05-02T17:55:38Z)
• 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)
• Learning to Simulate Realistic LiDARs [66.7519667383175]
  We introduce a pipeline for data-driven simulation of a realistic LiDAR sensor. We show that our model can learn to encode realistic effects such as dropped points on transparent surfaces. We use our technique to learn models of two distinct LiDAR sensors and use them to improve simulated LiDAR data accordingly.
  arXiv  Detail & Related papers  (2022-09-22T13:12:54Z)
• LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Clouds [58.402752909624716]
  Existing motion capture datasets are largely short-range and cannot yet fit the need of long-range applications. We propose LiDARHuman26M, a new human motion capture dataset captured by LiDAR at a much longer range to overcome this limitation. Our dataset also includes the ground truth human motions acquired by the IMU system and the synchronous RGB images.
  arXiv  Detail & Related papers  (2022-03-28T12:52:45Z)

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.