{"ID":2846684,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.01541","arxiv_id":"2511.01541","title":"Driving scenario generation and evaluation using a structured layer representation and foundational models","abstract":"Rare and challenging driving scenarios are critical for autonomous vehicle development. Since they are difficult to encounter, simulating or generating them using generative models is a popular approach. Following previous efforts to structure driving scenario representations in a layer model, we propose a structured five-layer model to improve the evaluation and generation of rare scenarios. We use this model alongside large foundational models to generate new driving scenarios using a data augmentation strategy. Unlike previous representations, our structure introduces subclasses and characteristics for every agent of the scenario, allowing us to compare them using an embedding specific to our layer-model. We study and adapt two metrics to evaluate the relevance of a synthetic dataset in the context of a structured representation: the diversity score estimates how different the scenarios of a dataset are from one another, while the originality score calculates how similar a synthetic dataset is from a real reference set. This paper showcases both metrics in different generation setup, as well as a qualitative evaluation of synthetic videos generated from structured scenario descriptions. The code and extended results can be found at https://github.com/Valgiz/5LMSG.","short_abstract":"Rare and challenging driving scenarios are critical for autonomous vehicle development. Since they are difficult to encounter, simulating or generating them using generative models is a popular approach. Following previous efforts to structure driving scenario representations in a layer model, we propose a structured f...","url_abs":"https://arxiv.org/abs/2511.01541","url_pdf":"https://arxiv.org/pdf/2511.01541v1","authors":"[\"Arthur Hubert\",\"Gamal Elghazaly\",\"Raphaël Frank\"]","published":"2025-11-03T13:04:55Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":607452,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2846684,"paper_url":"https://arxiv.org/abs/2511.01541","paper_title":"Driving scenario generation and evaluation using a structured layer representation and foundational models","repo_url":"https://github.com/Valgiz/5LMSG","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}