SynthDrive: Scalable Real2Sim2Real Sensor Simulation Pipeline for High-Fidelity Asset Generation and Driving Data Synthesis

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Zhengqing, Mei, Ruohong, Guo, Xiaoyang, Wang, Qingjie, Hu, Yubin, Yin, Wei, Ren, Weiqiang, Zhang, Qian
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911142927925248
author Chen, Zhengqing
Mei, Ruohong
Guo, Xiaoyang
Wang, Qingjie
Hu, Yubin
Yin, Wei
Ren, Weiqiang
Zhang, Qian
author_facet Chen, Zhengqing
Mei, Ruohong
Guo, Xiaoyang
Wang, Qingjie
Hu, Yubin
Yin, Wei
Ren, Weiqiang
Zhang, Qian
contents In the field of autonomous driving, sensor simulation is essential for generating rare and diverse scenarios that are difficult to capture in real-world environments. Current solutions fall into two categories: 1) CG-based methods, such as CARLA, which lack diversity and struggle to scale to the vast array of rare cases required for robust perception training; and 2) learning-based approaches, such as NeuSim, which are limited to specific object categories (vehicles) and require extensive multi-sensor data, hindering their applicability to generic objects. To address these limitations, we propose a scalable real2sim2real system that leverages 3D generation to automate asset mining, generation, and rare-case data synthesis.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06798
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SynthDrive: Scalable Real2Sim2Real Sensor Simulation Pipeline for High-Fidelity Asset Generation and Driving Data Synthesis
Chen, Zhengqing
Mei, Ruohong
Guo, Xiaoyang
Wang, Qingjie
Hu, Yubin
Yin, Wei
Ren, Weiqiang
Zhang, Qian
Computer Vision and Pattern Recognition
In the field of autonomous driving, sensor simulation is essential for generating rare and diverse scenarios that are difficult to capture in real-world environments. Current solutions fall into two categories: 1) CG-based methods, such as CARLA, which lack diversity and struggle to scale to the vast array of rare cases required for robust perception training; and 2) learning-based approaches, such as NeuSim, which are limited to specific object categories (vehicles) and require extensive multi-sensor data, hindering their applicability to generic objects. To address these limitations, we propose a scalable real2sim2real system that leverages 3D generation to automate asset mining, generation, and rare-case data synthesis.
title SynthDrive: Scalable Real2Sim2Real Sensor Simulation Pipeline for High-Fidelity Asset Generation and Driving Data Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.06798