SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Hess, Georg, Lindström, Carl, Fatemi, Maryam, Petersson, Christoffer, Svensson, Lennart
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916651651301376
author Hess, Georg
Lindström, Carl
Fatemi, Maryam
Petersson, Christoffer
Svensson, Lennart
author_facet Hess, Georg
Lindström, Carl
Fatemi, Maryam
Petersson, Christoffer
Svensson, Lennart
contents Ensuring the safety of autonomous robots, such as self-driving vehicles, requires extensive testing across diverse driving scenarios. Simulation is a key ingredient for conducting such testing in a cost-effective and scalable way. Neural rendering methods have gained popularity, as they can build simulation environments from collected logs in a data-driven manner. However, existing neural radiance field (NeRF) methods for sensor-realistic rendering of camera and lidar data suffer from low rendering speeds, limiting their applicability for large-scale testing. While 3D Gaussian Splatting (3DGS) enables real-time rendering, current methods are limited to camera data and are unable to render lidar data essential for autonomous driving. To address these limitations, we propose SplatAD, the first 3DGS-based method for realistic, real-time rendering of dynamic scenes for both camera and lidar data. SplatAD accurately models key sensor-specific phenomena such as rolling shutter effects, lidar intensity, and lidar ray dropouts, using purpose-built algorithms to optimize rendering efficiency. Evaluation across three autonomous driving datasets demonstrates that SplatAD achieves state-of-the-art rendering quality with up to +2 PSNR for NVS and +3 PSNR for reconstruction while increasing rendering speed over NeRF-based methods by an order of magnitude. See https://research.zenseact.com/publications/splatad/ for our project page.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16816
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving
Hess, Georg
Lindström, Carl
Fatemi, Maryam
Petersson, Christoffer
Svensson, Lennart
Computer Vision and Pattern Recognition
Graphics
Ensuring the safety of autonomous robots, such as self-driving vehicles, requires extensive testing across diverse driving scenarios. Simulation is a key ingredient for conducting such testing in a cost-effective and scalable way. Neural rendering methods have gained popularity, as they can build simulation environments from collected logs in a data-driven manner. However, existing neural radiance field (NeRF) methods for sensor-realistic rendering of camera and lidar data suffer from low rendering speeds, limiting their applicability for large-scale testing. While 3D Gaussian Splatting (3DGS) enables real-time rendering, current methods are limited to camera data and are unable to render lidar data essential for autonomous driving. To address these limitations, we propose SplatAD, the first 3DGS-based method for realistic, real-time rendering of dynamic scenes for both camera and lidar data. SplatAD accurately models key sensor-specific phenomena such as rolling shutter effects, lidar intensity, and lidar ray dropouts, using purpose-built algorithms to optimize rendering efficiency. Evaluation across three autonomous driving datasets demonstrates that SplatAD achieves state-of-the-art rendering quality with up to +2 PSNR for NVS and +3 PSNR for reconstruction while increasing rendering speed over NeRF-based methods by an order of magnitude. See https://research.zenseact.com/publications/splatad/ for our project page.
title SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2411.16816