diff --git a/README.md b/README.md index f0b3988..21e9040 100644 --- a/README.md +++ b/README.md @@ -2,24 +2,32 @@ VTON-IT: Virtual Try-On using Image Translation +
+ Paper   | +   Github   | +   Video +
-

+
+

This paper introduces VTON-IT, a novel Virtual Try-On application that uses semantic segmentation and a generative adversarial network to produce high-resolution, natural-looking images of clothes overlaid onto segmented body regions, addressing the challenges of body size, pose, and occlusions.

+

+Below is the overview of proposed VTON-IT. First, the human body is detected and cropped. Then, the desired body region is segmented through U2-Net architecture and the segmented mask is fed to the image translation network to generate wrapped cloth. Finally, the wrapped cloth is overlayed over the input image. +

-
- Project Page | - Paper | - Video -
- +

+ +

+## Result +For evaluating the performance of VTON-IT through visual observation, we compared the final overlayed images with the output of CP-VTON+. Image below shows that the proposed virtual try-on application produces more realistic and convincing results in terms of texture transfer quality and pose preservation. -
- -
+

+ +

## Requirements @@ -30,29 +38,31 @@ - opencv ## Training Pix2pix: + ``` - python3 train.py --label_nc 0 --no_instance --name vd2.0_2 --dataroot ./datasets/vd2.0_2 --continue_train --gpu_ids 0,1 --batchSize 2 + python3 train.py --label_nc 0 --no_instance --name vd2.0_2 --dataroot ./datasets/vd2.0_2 --continue_train --gpu_ids 0,1 --batchSize 2 ``` ## Train Segmentation model + ``` u2net_train.py ``` - ## Inference + ``` Inference.py ``` ## Reference -If you find this repo helpful, please consider citing: +If you find our paper and code useful in your research, please consider giving a star ⭐ and citation 📝 :) ``` @misc{adhikari2023vtonit, - title={VTON-IT: Virtual Try-On using Image Translation}, + title={VTON-IT: Virtual Try-On using Image Translation}, author={Santosh Adhikari and Bishnu Bhusal and Prashant Ghimire and Anil Shrestha}, year={2023}, eprint={2310.04558}, @@ -62,10 +72,5 @@ If you find this repo helpful, please consider citing: ``` ## Acknowledgements - The authors would like to thank IKebana Solutions LLC for providing them with constant support for this research project. - - - - - +The authors would like to thank IKebana Solutions LLC for providing them with constant support for this research project. diff --git a/assets/comparision.png b/assets/comparision.png new file mode 100644 index 0000000..f6cb4ff Binary files /dev/null and b/assets/comparision.png differ diff --git a/final_overlay.jpg b/assets/final_overlay.jpg similarity index 100% rename from final_overlay.jpg rename to assets/final_overlay.jpg diff --git a/assets/overview.png b/assets/overview.png new file mode 100644 index 0000000..c67d5d3 Binary files /dev/null and b/assets/overview.png differ