CloSe: A 3D Clothing Segmentation Dataset and Model

Abstract

3D Clothing modeling and datasets play crucial role in the entertainment, animation, and digital fashion industries. Existing work often lacks detailed semantic understanding or uses synthetic datasets, lacking realism and personalization. To address this, we first introduce CloSe-D: a novel large-scale dataset containing 3D clothing segmentation of 3167 scans, covering a range of 18 distinct clothing classes. Additionally, we propose CloSe-Net, the first learning-based 3D clothing segmentation model for fine-grained segmentation from colored point clouds. CloSe-Net uses local point features, body-clothing correlation, and a garment-class and point features-based attention module, improving performance over baselines and prior work. The proposed attention module enables our model to learn appearance and geometry-dependent clothing prior from data. We further validate the efficacy of our approach by successfully segmenting publicly available datasets of people in clothing. We also introduce CloSe-T, a 3D interactive tool for refining segmentation labels. Combining the tool with CloSe-Net in a continual learning setup demonstrates improved generalization on real-world data.

Citation

@inproceedings{antic2024close,
    title = {CloSe: A 3D Clothing Segmentation Dataset and Model},
    author = {Antić, Dimitrije and Tiwari, Garvita and Ozcomlekci, Batuhan  and Marin, Riccardo  and Pons-Moll, Gerard},
    booktitle = {International Conference on 3D Vision (3DV)},
    month = {March},
    year = {2024},
    }

Acknowledgments

Thanks to RVH, CVLab team, and reviewers for valuable feedback. The project was made possible by funding from the Carl Zeiss Foundation. This work is supported by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - 409792180 (Emmy Noether Programme, project: Real Virtual Humans), German Federal Ministry of Education and Research (BMBF): Tübingen AI Center, FKZ: 01IS18039A. Gerard Pons-Moll is a member of the Machine Learning Cluster of Excellence, EXC number 2064/1 - Project number 390727645. Riccardo Marin has been supported by the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie grant agreement No 101109330. Website is based on StyleGAN3 and Nerfies websites.