SPRIGHT
Introduced by Chatterjee et al. in Getting it Right: Improving Spatial Consistency in Text-to-Image Models
SPRIGHT is the first, large-scale vision-language dataset that focuses on spatial relationships. It contains ~6M images that have been re-captioned with a synthetic focus.
Papers
| Paper | Code | Results | Date | Stars |
|---|
Dataset Loaders
No data loaders found. You can
submit your data loader here.
No data loaders found. You can
submit your data loader here.
