CS470-project

Virtual-try-on with clothes cropping

Dataset and reference

[Dataset Partition Label] [Sample Try-on Video] [Checkpoints]

[Dataset_Test] [Dataset_Train]

[Paper]

Pre-trained model

[Deep Fahion pre-trained] [Vgg19 pre-trained]

Our trained model(clothes masking)

[Trained model]

Inference

For Virtual-try-on,

cd DeepFashion_Try_On
python main.py --phase test

For Clothes masking & cropping

cd Cloth_mask
python test.py

Sample Cloth mask Results

Sample Try-on Results

Training Details

For better inference performance, model G and G2 should be trained with 200 epoches, while model G1 and U net should be trained with 20 epoches. For Cloth mask, training with 100 epoches works well.

License

The use of this software is RESTRICTED to non-commercial research and educational purposes.

Dataset

VITON Dataset This dataset is presented in VITON, containing 19,000 image pairs, each of which includes a front-view woman image and a top clothing image. After removing the invalid image pairs, it yields 16,253 pairs, further splitting into a training set of 14,221 paris and a testing set of 2,032 pairs.