Watermark Remover

Disclaimer: This project was made to showcase my Deep Learning skills with no intention to cause harm to any business or infringe on any IP and it will be decommissioned as soon as I get a decent job offer. If you still have any issue, please reach out to me at bhu.aryan.28@gmail.com.

This is a demo of a DL model which takes in an image with a watermark (either via URL or direct upload) and gives out the image with its watermark removed. The image is broken into overlapping patches of 256x256 pixels with a stride of 64 before feeding them to the model, the model infers on each patch separately and then they are stitched together to form the whole image again to give the final output.

Image URL

Enter the direct link to a publicly accessible image file.

Or Upload Image File

Click on the link to upload some test examples

Some Samples

Watermarked Image vs Processed Image

Your Uploaded Image

Processed Output Image

A bit about the model: In this project, I have trained a GAN network, with the Generator being inspired from Pix2Pix and Pix2PixHD architectures and the Discriminator is very similar to PatchGAN in Pix2Pix. For the loss, I have also added Perceptual Loss using VGG like in Pix2PixHD and SRGAN papers apart from the L1 and BCE loss.

If you liked this project, you can find my CV here or reach me out at bhu.aryan.28@gmail.com.