Exploring Generative AI for Sim2Real in Driving Data Synthesis

arXiv:2404.09111v1 Announce Type: new
Abstract: Datasets are essential for training and testing vehicle perception algorithms. However, the collection and annotation of real-world images is time-consuming and expensive. Driving simulators offer a solution by automatically generating various driving scenarios with corresponding annotations, but the simulation-to-reality (Sim2Real) domain gap remains a challenge. While most of the Generative Artificial Intelligence (AI) follows the de facto Generative Adversarial Nets (GANs)-based methods, the recent emerging diffusion probabilistic models have not been fully explored in mitigating …

abstract algorithms annotation annotations arxiv challenge collection cs.cv data datasets domain driving driving data gap generative however images perception reality simulation solution synthesis testing the simulation training type world