Alexandros Delitzas¹, Ayça Takmaz¹
Federico Tombari^2,3, Robert W. Sumner¹, Marc Pollefeys^1,4, Francis Engelmann^1,2
1ETH Zurich, ²Google, ³TUM, ⁴Microsoft

This repository contains the code for the SceneFun3D Toolkit. Please refer to the documentation page for information and detailed instructions.

Check the Changelog for detailed updates (Last update: 10/03/2025)

• March 10, 2025: The benchmark submission portal is now live. Check out the updated submission instructions and the changelog.
• October 10, 2024: Initial release.

Project documentation can be found here: https://scenefun3d.github.io/documentation.

• Project page
• Documentation
• Paper
• Github repositories
• Data downloader instructions
• Benchmark submission portal
• Benchmark instructions

If you find our work useful for your research, please consider citing as:

@inproceedings{delitzas2024scenefun3d, 
  title = {{SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes}}, 
  author = {Delitzas, Alexandros and Takmaz, Ayca and Tombari, Federico and Sumner, Robert and Pollefeys, Marc and Engelmann, Francis}, 
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, 
  year = {2024}
}