Awesome

SIZER: A DATASET AND MODEL FOR PARSING 3D CLOTHING AND LEARNING SIZE SENSITIVE 3D CLOTHING

For SIZER Dataset:

https://github.com/garvita-tiwari/sizer_dataset

Code and model for SIZER: A DATASET AND MODEL FOR PARSING 3D CLOTHING AND LEARNING SIZE SENSITIVE 3D CLOTHING, ECCV 2020(Oral)

• Website
• Dataset and Model (Drop a mail to : gtiwari@mpi-inf.mpg.de(or garvita.tiwari@uni-tuebingen.de) for getting access to dataset)
• Fill this form for dataset

###SIZER Dataset: https://github.com/garvita-tiwari/sizer_dataset

Data path:

set DATA_DIR='<downloaded dataset path>/training_data' in utils/global_var.py 

Conda Environment:

conda create --name sizer --file requirements.txt
conda activate sizer

Training ParserNet:

python trainer.py --config=<configs/parser_default.yaml>

Evaluating ParserNet:

python generate.py --config=<configs/parser_default.yaml>

Training SizerNet:

python  trainer.py --config=<configs/sizer_default.yaml>

Evaluating SizerNet:

python generate.py --config=<configs/sizer_default.yaml>

If you are using SIZER dataset and models, please cite:

@inproceedings{tiwari20sizer,
    title = {SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing},
    author = {Tiwari, Garvita and Bhatnagar, Bharat Lal and Tung, Tony and Pons-Moll, Gerard},
    booktitle = {European Conference on Computer Vision ({ECCV})},
    month = {August},
    organization = {{Springer}},
    year = {2020},
    }

@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},
}

Also refer to CloSe for diverse poses of SIZER dataset and more accurate and fine-grained clothing segmentaion.

Acknowledgements:

Thanks to Chaitanya Patel for pytorch implementation of SMPL4Garment (Link: https://github.com/chaitanya100100/TailorNet)