# Visual Watermark Removal Based on Deep Learning

arXiv: https://arxiv.org/abs/2302.11338 · HTML: https://mlsanity.com/paper/2302.11338/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 11 references that are in the map.
- First posted on arXiv 7 Feb 2023.

## Builds on (most cited first, 9 of 9)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [Improving the Harmony of the Composite Image by Spatial-Separated Attention Module](https://mlsanity.com/paper/1907.06406/) (2019)
- [WDNet: Watermark-Decomposition Network for Visible Watermark Removal](https://mlsanity.com/paper/2012.07616/) (2020)
- [Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal](https://mlsanity.com/paper/2012.07007/) (2020)
- [Blind Visual Motif Removal from a Single Image](https://mlsanity.com/paper/1904.02756/) (2019)
- [Visible Watermark Removal via Self-calibrated Localization and Background Refinement](https://mlsanity.com/paper/2108.03581/) (2021)

## Abstract (arXiv)

In recent years as the internet age continues to grow, sharing images on social media has become a common occurrence. In certain cases, watermarks are used as protection for the ownership of the image, however, in more cases, one may wish to remove these watermark images to get the original image without obscuring. In this work, we proposed a deep learning method based technique for visual watermark removal. Inspired by the strong image translation performance of the U-structure, an end-to-end deep neural network model named AdvancedUnet is proposed to extract and remove the visual watermark simultaneously. On the other hand, we embed some effective RSU module instead of the common residual block used in UNet, which increases the depth of the whole architecture without significantly increasing the computational cost. The deep-supervised hybrid loss guides the network to learn the transformation between the input image and the ground truth in a multi-scale and three-level hierarchy. Comparison experiments demonstrate the effectiveness of our method.