# A self-supervised CNN for image watermark removal

arXiv: https://arxiv.org/abs/2403.05807 · HTML: https://mlsanity.com/paper/2403.05807/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 45 references that are in the map.
- First posted on arXiv 9 Mar 2024.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [MemNet: A Persistent Memory Network for Image Restoration](https://mlsanity.com/paper/1708.02209/) (2017)
- [REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Data](https://mlsanity.com/paper/1911.07205/) (2019)
- [WDNet: Watermark-Decomposition Network for Visible Watermark Removal](https://mlsanity.com/paper/2012.07616/) (2020)
- [RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images](https://mlsanity.com/paper/2110.14223/) (2021)
- [Global-and-Local Collaborative Learning for Co-Salient Object Detection](https://mlsanity.com/paper/2204.08917/) (2022)
- [Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal](https://mlsanity.com/paper/2012.07007/) (2020)
- [DRD-Net: Detail-recovery Image Deraining via Context Aggregation Networks](https://mlsanity.com/paper/1908.10267/) (2019)
- [Asymmetric CNN for image super-resolution](https://mlsanity.com/paper/2103.13634/) (2021)
- [Towards Photo-Realistic Visible Watermark Removal with Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1905.12845/) (2019)

## Built on by (most cited first, 3 of 3)

- [Box-Free Model Watermarks Are Prone to Black-Box Removal Attacks](https://mlsanity.com/paper/2405.09863/) (2024)
- [Template-based Object Detection Using a Foundation Model](https://mlsanity.com/paper/2603.19773/) (2026)
- [Reversible Unlearnable Examples: Towards the Copyright Protection in Deep Learning Era](https://mlsanity.com/paper/2608.06211/) (2026)

## Abstract (arXiv)

Popular convolutional neural networks mainly use paired images in a supervised way for image watermark removal. However, watermarked images do not have reference images in the real world, which results in poor robustness of image watermark removal techniques. In this paper, we propose a self-supervised convolutional neural network (CNN) in image watermark removal (SWCNN). SWCNN uses a self-supervised way to construct reference watermarked images rather than given paired training samples, according to watermark distribution. A heterogeneous U-Net architecture is used to extract more complementary structural information via simple components for image watermark removal. Taking into account texture information, a mixed loss is exploited to improve visual effects of image watermark removal. Besides, a watermark dataset is conducted. Experimental results show that the proposed SWCNN is superior to popular CNNs in image watermark removal.