SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models

Project Page | Paper | arXiv | HuggingFace Model | HuggingFace Space | Dataset | Twitter/X | YouTube Video

Turhan Can Kargin, Wojciech Jasiński, Adam Pardyl, Bartosz Zieliński, Marcin Przewięźlikowski

📰 NEWS:

• Mar. 2026: Model and demo space are available on HuggingFace Model and HuggingFace Space.
• Mar. 2026: Scene generation pipeline is available on GitHub.
• Mar. 2026: Dataset is available on HuggingFace.
• Jan. 2026: Codebase will be released soon!
• Jan. 2026: Paper is available on arXiv.

---

If you find this research useful, please consider citing:

@misc{kargin2026sparrta,
  title={SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models},
  author={Turhan Can Kargin and Wojciech Jasiński and Adam Pardyl and Bartosz Zieliński and Marcin Przewięźlikowski},
  year={2026},
  eprint={2601.11729},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2601.11729}
}