VITON-flask
A multi-stage virtual try-on deep neural networks based on JPP-Net and CP-VTON. We provide SIMPLE and EASY-to-handle API on upper level, and combine some traditional image processing methods.
Feature:
- Fast Human_Image + Cloth_Image = Gen_Image, put on a specified upper clothes for specified people.
- Web and Backend response service on Flask
How to use
CPU Mode: Model(.., use_cuda = False)
References
Model designs are based on JPP-Net & CPVTON, and their open-source repo on Github.
VITON: An Image-based Virtual Try-on Network,Xintong Han, Zuxuan Wu, Zhe Wu, Ruichi Yu, Larry S. Davis. CVPR 2018
(CP-VTON) Toward Characteristic-Preserving Image-based Virtual Try-On Networks, Bochao Wang, Huabin Zheng, Xiaodan Liang, Yimin Chen, Liang Lin, Meng Yang. ECCV 2018
(JPP-Net) Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark, Xiaodan Liang, Ke Gong, Xiaohui Shen, Liang Lin, T-PAMI 2018.