BEV-LLM: Leveraging Multimodal BEV Maps for Scene Captioning in Autonomous Driving

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Brandstaetter, Felix, Schuetz, Erik, Winter, Katharina, Flohr, Fabian
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909705358540800
author Brandstaetter, Felix
Schuetz, Erik
Winter, Katharina
Flohr, Fabian
author_facet Brandstaetter, Felix
Schuetz, Erik
Winter, Katharina
Flohr, Fabian
contents Autonomous driving technology has the potential to transform transportation, but its wide adoption depends on the development of interpretable and transparent decision-making systems. Scene captioning, which generates natural language descriptions of the driving environment, plays a crucial role in enhancing transparency, safety, and human-AI interaction. We introduce BEV-LLM, a lightweight model for 3D captioning of autonomous driving scenes. BEV-LLM leverages BEVFusion to combine 3D LiDAR point clouds and multi-view images, incorporating a novel absolute positional encoding for view-specific scene descriptions. Despite using a small 1B parameter base model, BEV-LLM achieves competitive performance on the nuCaption dataset, surpassing state-of-the-art by up to 5\% in BLEU scores. Additionally, we release two new datasets - nuView (focused on environmental conditions and viewpoints) and GroundView (focused on object grounding) - to better assess scene captioning across diverse driving scenarios and address gaps in current benchmarks, along with initial benchmarking results demonstrating their effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2507_19370
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BEV-LLM: Leveraging Multimodal BEV Maps for Scene Captioning in Autonomous Driving
Brandstaetter, Felix
Schuetz, Erik
Winter, Katharina
Flohr, Fabian
Computer Vision and Pattern Recognition
Autonomous driving technology has the potential to transform transportation, but its wide adoption depends on the development of interpretable and transparent decision-making systems. Scene captioning, which generates natural language descriptions of the driving environment, plays a crucial role in enhancing transparency, safety, and human-AI interaction. We introduce BEV-LLM, a lightweight model for 3D captioning of autonomous driving scenes. BEV-LLM leverages BEVFusion to combine 3D LiDAR point clouds and multi-view images, incorporating a novel absolute positional encoding for view-specific scene descriptions. Despite using a small 1B parameter base model, BEV-LLM achieves competitive performance on the nuCaption dataset, surpassing state-of-the-art by up to 5\% in BLEU scores. Additionally, we release two new datasets - nuView (focused on environmental conditions and viewpoints) and GroundView (focused on object grounding) - to better assess scene captioning across diverse driving scenarios and address gaps in current benchmarks, along with initial benchmarking results demonstrating their effectiveness.
title BEV-LLM: Leveraging Multimodal BEV Maps for Scene Captioning in Autonomous Driving
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.19370