RoadSceneBench: A Lightweight Benchmark for Mid-Level Road Scene Understanding
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911291693596672 |
|---|---|
| author | Liu, Xiyan Wang, Han Wang, Yuhu Cai, Junjie Cao, Zhe Yang, Jianzhong Lu, Zhen |
| author_facet | Liu, Xiyan Wang, Han Wang, Yuhu Cai, Junjie Cao, Zhe Yang, Jianzhong Lu, Zhen |
| contents | Understanding mid-level road semantics, which capture the structural and contextual cues that link low-level perception to high-level planning, is essential for reliable autonomous driving and digital map construction. However, existing benchmarks primarily target perception tasks such as detection or segmentation, overlooking the reasoning capabilities required to infer road topology and dynamic scene structure. To address this gap, we present RoadSceneBench, a lightweight yet information-rich benchmark designed to evaluate and advance visual reasoning in complex road environments. Unlike large-scale perception datasets, RoadSceneBench emphasizes relational understanding and structural consistency, encouraging models to capture the underlying logic of real-world road scenes. Furthermore, to enhance reasoning reliability, we propose Hierarchical Relational Reward Propagation with Temporal Consistency (HRRP-T), a training framework for Vision-Language Models (VLMs) in which reward signals adaptively promote spatial coherence and semantic alignment throughout the reasoning process. This paradigm enables models to move beyond static recognition toward geometry-aware and temporally consistent reasoning. Extensive experiments demonstrate that our method achieves state-of-the-art performance across diverse road configurations. RoadSceneBench thus provides a compact yet powerful foundation for studying mid-level road semantics and fostering structure-aware autonomous perception. Our dataset is available at https://github.com/XiyanLiu/RoadSceneBench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22466 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RoadSceneBench: A Lightweight Benchmark for Mid-Level Road Scene Understanding Liu, Xiyan Wang, Han Wang, Yuhu Cai, Junjie Cao, Zhe Yang, Jianzhong Lu, Zhen Computer Vision and Pattern Recognition Understanding mid-level road semantics, which capture the structural and contextual cues that link low-level perception to high-level planning, is essential for reliable autonomous driving and digital map construction. However, existing benchmarks primarily target perception tasks such as detection or segmentation, overlooking the reasoning capabilities required to infer road topology and dynamic scene structure. To address this gap, we present RoadSceneBench, a lightweight yet information-rich benchmark designed to evaluate and advance visual reasoning in complex road environments. Unlike large-scale perception datasets, RoadSceneBench emphasizes relational understanding and structural consistency, encouraging models to capture the underlying logic of real-world road scenes. Furthermore, to enhance reasoning reliability, we propose Hierarchical Relational Reward Propagation with Temporal Consistency (HRRP-T), a training framework for Vision-Language Models (VLMs) in which reward signals adaptively promote spatial coherence and semantic alignment throughout the reasoning process. This paradigm enables models to move beyond static recognition toward geometry-aware and temporally consistent reasoning. Extensive experiments demonstrate that our method achieves state-of-the-art performance across diverse road configurations. RoadSceneBench thus provides a compact yet powerful foundation for studying mid-level road semantics and fostering structure-aware autonomous perception. Our dataset is available at https://github.com/XiyanLiu/RoadSceneBench. |
| title | RoadSceneBench: A Lightweight Benchmark for Mid-Level Road Scene Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.22466 |