Abstract

---

We present 3D CoMPaT, a richly annotated large-scale dataset of more than 7.19 million rendered compositions of Materials on Parts of 7262 unique 3D Models; 990 compositions per model on average. 3DCoMPaT covers 43 shape categories, 235 unique part names, and 167 unique material classes that can be applied to parts of 3D objects. Each object with the applied part-material compositions is rendered from four equally spaced views as well as four randomized views, leading to a total of 58 million renderings (7.19 million compositions x8 views). This dataset primarily focuses on stylizing 3D shapes at part-level with compatible materials. We introduce a new task, called Grounded CoMPaT Recognition (GCR), to collectively recognize and ground compositions of materials on parts of 3D objects. We present two variations of this task and adapt state-of-art 2D/3D deep learning methods to solve the problem as baselines for future research. We hope our work will help ease future research on compositional 3D Vision.

Video

---

Dataset

---

Downloading

You can download 3DCoMPaT after filling the following form:



3DCoMPaT Agreement

Browser

You can browse the 3D models using the following link:



3DCoMPaT browser

Acknowledgements

For computer time, this research used the resources of the Supercomputing Laboratory at King Abdullah University of Science & Technology (KAUST) in Thuwal, Saudi Arabia. We also acknowledge Tezuesh Varshney for contributing to data collection in the earlier version of the dataset.

Citation

---

If our paper is helpful for your work, please consider citing us:

@inproceedings{li20223d_compat,
title={{3DCoMPaT}: Composition of Materials on Parts of 3D Things},
author={Yuchen Li, Ujjwal Upadhyay, Habib Slim,
    Ahmed Abdelreheem, Arpit Prajapati,
    Suhail Pothigara, Peter Wonka, Mohamed Elhoseiny},
booktitle={17th European Conference on Computer Vision (ECCV)},
year={2022}
}