EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929378991013888 |
|---|---|
| author | Du, Mengfei Wu, Binhao Li, Zejun Huang, Xuanjing Wei, Zhongyu |
| author_facet | Du, Mengfei Wu, Binhao Li, Zejun Huang, Xuanjing Wei, Zhongyu |
| contents | The recent rapid development of Large Vision-Language Models (LVLMs) has indicated their potential for embodied tasks.However, the critical skill of spatial understanding in embodied environments has not been thoroughly evaluated, leaving the gap between current LVLMs and qualified embodied intelligence unknown. Therefore, we construct EmbSpatial-Bench, a benchmark for evaluating embodied spatial understanding of LVLMs.The benchmark is automatically derived from embodied scenes and covers 6 spatial relationships from an egocentric perspective.Experiments expose the insufficient capacity of current LVLMs (even GPT-4V). We further present EmbSpatial-SFT, an instruction-tuning dataset designed to improve LVLMs' embodied spatial understanding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_05756 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models Du, Mengfei Wu, Binhao Li, Zejun Huang, Xuanjing Wei, Zhongyu Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Multimedia The recent rapid development of Large Vision-Language Models (LVLMs) has indicated their potential for embodied tasks.However, the critical skill of spatial understanding in embodied environments has not been thoroughly evaluated, leaving the gap between current LVLMs and qualified embodied intelligence unknown. Therefore, we construct EmbSpatial-Bench, a benchmark for evaluating embodied spatial understanding of LVLMs.The benchmark is automatically derived from embodied scenes and covers 6 spatial relationships from an egocentric perspective.Experiments expose the insufficient capacity of current LVLMs (even GPT-4V). We further present EmbSpatial-SFT, an instruction-tuning dataset designed to improve LVLMs' embodied spatial understanding. |
| title | EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models |
| topic | Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2406.05756 |