Autonomous driving has seen remarkable advancements, largely driven by extensive real-world data collection. However, acquiring diverse and corner-case data remains costly and inefficient. Generative models have emerged as a promising solution by synthesizing realistic sensor data. However, existing approaches primarily focus on single-modality generation, leading to inefficiencies and misalignment in multimodal sensor data. To address these challenges, we propose OminiGen, which generates aligned multimodal sensor data in a unified framework. Our approach leverages a shared Bird\u2019s Eye View (BEV) space to unify multimodal features and designs a novel generalizable multimodal reconstruction method, UAE, to jointly decode LiDAR and multi-view camera data. UAE achieves multimodal sensor decoding through volume rendering, enabling accurate and flexible reconstruction. Furthermore, we incorporate a Diffusion Transformer (DiT) with a ControlNet branch to enable controllable multimodal sensor generation. Our comprehensive experiments demonstrate that OminiGen achieves desired performances in unified multimodal sensor data generation with multimodal consistency and flexible sensor adjustments.
@article{arxiv.2512.14225,
title = {OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving},
author = {Tao Tang and Enhui Ma and xia zhou and Letian Wang and Tianyi Yan and Xueyang Zhang and Kun Zhan and Peng Jia and XianPeng Lang and Jia-Wang Bian and Kaicheng Yu and Xiaodan Liang},
journal= {arXiv preprint arXiv:2512.14225},
year = {2025}
}