READ: Large-Scale Neural Scene Rendering for Autonomous Driving

作者：Zhuopeng Li, Lu Li, Zeyu Ma, Ping Zhang, Junbo Chen, Jian-Zong Zhu · 发表于：AAAI Conference on Artificial Intelligence · 年份：2022 · DOI：10.48550/arXiv.2205.05509 · 被引用次数：80 · 研究领域：Computer Science

With the development of advanced driver assistance systems~(ADAS) and autonomous vehicles, conducting experiments in various scenarios becomes an urgent need. Although having been capable of synthesizing photo-realistic street scenes, conventional image-to-image translation methods cannot produce coherent scenes due to the lack of 3D information. In this paper, a large-scale neural rendering method is proposed to synthesize the autonomous driving scene~(READ), which makes it possible to generate large-scale driving scenes in real time on a PC through a variety of sampling schemes. In order to effectively represent driving scenarios, we propose an ω-net rendering network to learn neural descriptors from sparse point clouds. Our model can not only synthesize photo-realistic driving scenes but also stitch and edit them. The promising experimental results show that our model performs well in large-scale driving scenarios.