The dataset and code are still currently being updated, partially due to the scale of the project. A full release will be available in time for ECCV 2022


3DCoMPaT: Composition of Materials on Parts of 3D Things
ECCV 2022, Oral


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 ×8 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.

Dataset


Downloading


Browser


Citation


If our paper is helpful for your work, please consider citing us:
@inproceedings{upadhyay20223d_compat,
    title={{3DCoMPaT}: Composition of Materials on Parts of 3D Things},
    author={Upadhyay, Ujjwal and Li, Yuchen and Slim, Habib and Varshney, Tezuesh and
        Abdelreheem, Ahmed and Prajapati, Arpit and Pothigara, Suhail and Wonka, Peter and Elhoseiny, Mohamed.},
    booktitle={17th European Conference on Computer Vision (ECCV)},
    year={2022}
}