https://github.com/hasibzunair/fifa-demo

[BMVC'2022] Demo code for Fill in Fabrics: Body-Aware Self-Supervised Inpainting for Image-Based Virtual Try-On
https://github.com/hasibzunair/fifa-demo

Last synced: 4 days ago
JSON representation

[BMVC'2022] Demo code for Fill in Fabrics: Body-Aware Self-Supervised Inpainting for Image-Based Virtual Try-On

• Host: GitHub
• URL: https://github.com/hasibzunair/fifa-demo
• Owner: hasibzunair
• Created: 2021-11-08T15:42:56.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2022-10-13T23:46:39.000Z (about 2 years ago)
• Last Synced: 2023-03-06T17:48:12.113Z (over 1 year ago)
• Language: Python
• Homepage: https://huggingface.co/spaces/hasibzunair/fifa-tryon-demo
• Size: 15 MB
• Stars: 2
• Watchers: 3
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Demo of FIFA for Virtual Try-On ⚽

[colab-badge]: 

[![Open In Colab][colab-badge]](https://colab.research.google.com/github/hasibzunair/vton-demo/blob/main/demo.ipynb)

This is demo repo for our BMVC 2022 paper:


[Fill in Fabrics: Body-Aware Self-Supervised Inpainting for Image-Based Virtual Try-On](https://arxiv.org/abs/2210.00918)




Training details available in the official repo [fifa-tryon](https://github.com/hasibzunair/fifa-tryon).



     


    

    Figure 1. Final try-on outputs of our method with other recent try-on methods.

    



### Interactive app build using [Gradio](https://gradio.app/)

You can use the model as a simple UI made with gradio. See [gradio_app](https://github.com/dktunited/fifa_demo/tree/master/gradio_app) for details on how to run the app. This app currently works on a local machine with a GPU. Can be hosted on a GPU server.

Note: I attempted to do a CPU implementation first. Got running the try-on and pose estimator models on CPU. The issue is when getting the parsing results (i.e multi-class segmentation) using [this](https://github.com/hasibzunair/Self-Correction-Human-Parsing-for-ACGPN.git) for the person image. The pre-trained model uses [In-Place Activated BatchNorm](https://github.com/mapillary/inplace_abn) for memory-optimized training. The implementation of In-Place Activated BatchNorm is currently only for GPUs. 

### Acknowledgements

This inference codebase is modified from https://github.com/levindabhi/ACGPN to run custom models. The human parser and segmentation models are from https://github.com/hasibzunair/Self-Correction-Human-Parsing-for-ACGPN and https://github.com/hasibzunair/U-2-Net.