SceneFun3D

Fine-Grained Functionality and Affordance Understanding in 3D Scenes

CVPR 2024 (Oral)

Alexandros Delitzas¹, Ayça Takmaz¹ Federico Tombari^2,3, Robert W. Sumner¹, Marc Pollefeys^1,4, Francis Engelmann^{1,2 1}ETH Zurich, ²Google, ³TUM, ⁴Microsoft ## SceneFun3D Toolkit 🔧 This repository contains the code for the SceneFun3D Toolkit. Please refer to the [documentation page](https://scenefun3d.github.io/documentation) for information and detailed instructions. ## News 📢 Check the [**Changelog**](https://scenefun3d.github.io/documentation/changelog/) for detailed updates (*Last update*: 10/03/2025) - **March 10, 2025**: The [benchmark submission portal](https://eval.ai/web/challenges/challenge-page/2466/overview) is now live. Check out the updated [submission instructions](https://scenefun3d.github.io/documentation/benchmarks/guidelines/) and the [changelog](https://scenefun3d.github.io/documentation/changelog/). - **October 10, 2024**: Initial release. ## Documentation 📖 Project documentation can be found here: [https://scenefun3d.github.io/documentation](https://scenefun3d.github.io/documentation). ## Quick links 🔗 * Project page * Documentation * Paper * Github repositories * Data downloader instructions * Benchmark submission portal * Benchmark instructions ## BibTeX Citation 🙏 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}
}