@article{seeimagineplandiscoveringand,
  title = {SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors},
  author = {Chenyang Ma and Kai Lu and Ta-Ying Cheng and Niki Trigoni and Andrew Markham},
  year = {2024},
  eprint = {2403.13438},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.13438v5},
}