CrossPoint-378K is a large-scale dataset for cross-view point correspondence. This dataset contains 378K training samples designed to enhance vision-language models' capabilities in cross-view point correspondences.
Dataset Structure
The dataset contains the following file structure:
CrossPoint-378K/
├── CrossPoint-378K.json # Main data file (ShareGPT format)
├── image/ # Original images… See the full description on the dataset page: https://huggingface.co/datasets/WangYipu2002/CrossPoint-378K.
