Datasets:
Tasks:
Visual Question Answering
Modalities:
Image
Formats:
imagefolder
Languages:
English
Size:
< 1K
ArXiv:
License:
SpatialBench evaluates model performance on spatial understanding. We design positional, existence, counting, reaching and size comparasion tasks.
In this HF dataset, SpatialBench RGB & Depth images, questions, answers and meta data are provided.
Paper:
https://arxiv.org/abs/2406.13642
GitHub repo:
SpatialBot, a VLM with precise depth understanding:
- Downloads last month
- 279
Paper for RussRobin/SpatialBench
Paper
•
2406.13642
•
Published
•
2