MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving

Zirui Wu, Tianyu Liu, Liyi Luo, Zhide Zhong, Jianteng Chen +11 more
7/27/2023
cs.CV

No official code found. Best implementation: OPEN-AIR-SUN/mars (682 stars, Apache-2.0, last commit 2024-06-10).

Abstract

Nowadays, autonomous cars can drive smoothly in ordinary cases, and it is widely recognized that realistic sensor simulation will play a critical role in solving remaining corner cases by simulating them. To this end, we propose an autonomous driving simulator based upon neural radiance fields (NeRFs). Compared with existing works, ours has three notable features: (1) Instance-aware. Our simulator models the foreground instances and background environments separately with independent networks so that the static (e.g., size and appearance) and dynamic (e.g., trajectory) properties of instances can be controlled separately. (2) Modular. Our simulator allows flexible switching between different modern NeRF-related backbones, sampling strategies, input modalities, etc. We expect this modular design to boost academic progress and industrial deployment of NeRF-based autonomous driving simulation. (3) Realistic. Our simulator set new state-of-the-art photo-realism results given the best module selection. Our simulator will be open-sourced while most of our counterparts are not. Project page: https://open-air-sun.github.io/mars/.

View on arXivView PDF

Code Implementations(1)

OPEN-AIR-SUN/marsCommunity100%
Apache-2.0

MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving

68266Python, JavaScriptJul 17, 20232 years agoApache-2.0

Similar Papers

Car-Studio: Learning Car Radiance Fields from Single-View and Endless In-the-wild Images

88% match1 repo522023

Industrial-Grade Sensor Simulation via Gaussian Splatting: A Modular Framework for Scalable Editing and Full-Stack Validation

87% match2025

S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation

87% match2024

FlightForge: Advancing UAV Research with Procedural Generation of High-Fidelity Simulation and Integrated Autonomy

86% match1 repo302025

MapNeRF: Incorporating Map Priors into Neural Radiance Fields for Driving View Simulation

85% match2023

GarchingSim: An Autonomous Driving Simulator with Photorealistic Scenes and Minimalist Workflow

85% match1 repo482024

Cite this paper

@article{wu2023mars,
  title  = {MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving},
  author = {Zirui Wu and Tianyu Liu and Liyi Luo and Zhide Zhong and Jianteng Chen and Hongmin Xiao and Chao Hou and Haozhe Lou and Yuantao Chen and Runyi Yang and Yuxin Huang and Xiaoyu Ye and Zike Yan and Yongliang Shi and Yiyi Liao and Hao Zhao},
  year   = {2023},
  eprint = {2307.15058},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.15058v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.15058.svg)](https://codeofpaper.com/paper/2307.15058)

Discussion