# Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal

arXiv: https://arxiv.org/abs/2012.07007 · HTML: https://mlsanity.com/paper/2012.07007/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2020.

## Built on by (most cited first, 20 of 20)

- [Invisible Image Watermarks Are Provably Removable Using Generative AI](https://mlsanity.com/paper/2306.01953/) (2023)
- [TrustMark: Universal Watermarking for Arbitrary Resolution Images](https://mlsanity.com/paper/2311.18297/) (2023)
- [PromptFix: You Prompt and We Fix the Photo](https://mlsanity.com/paper/2405.16785/) (2024)
- [Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization](https://mlsanity.com/paper/2109.05750/) (2021)
- [Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal](https://mlsanity.com/paper/2207.08178/) (2022)
- [Visible Watermark Removal via Self-calibrated Localization and Background Refinement](https://mlsanity.com/paper/2108.03581/) (2021)
- [RemovalNet: DNN Fingerprint Removal Attacks](https://mlsanity.com/paper/2308.12319/) (2023)
- [Hierarchical Contrastive Learning for Pattern-Generalizable Image Corruption Detection](https://mlsanity.com/paper/2308.14061/) (2023)
- [Perceptive self-supervised learning network for noisy image watermark removal](https://mlsanity.com/paper/2403.02211/) (2024)
- [A self-supervised CNN for image watermark removal](https://mlsanity.com/paper/2403.05807/) (2024)
- [Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal](https://mlsanity.com/paper/2312.14383/) (2023)
- [Image Harmonization with Region-wise Contrastive Learning](https://mlsanity.com/paper/2205.14058/) (2022)
- [AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective](https://mlsanity.com/paper/2603.24857/) (2026)
- [Rooms with Text: A Dataset for Overlaying Text Detection](https://mlsanity.com/paper/2211.11350/) (2022)
- [Visual Watermark Removal Based on Deep Learning](https://mlsanity.com/paper/2302.11338/) (2023)
- [WMFormer++: Nested Transformer for Visible Watermark Removal via Implict Joint Learning](https://mlsanity.com/paper/2308.10195/) (2023)
- [Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal](https://mlsanity.com/paper/2504.04687/) (2025)
- [Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection](https://mlsanity.com/paper/2506.02665/) (2025)
- [SAiW: Source-Attributable Invisible Watermarking for Proactive Deepfake Defense](https://mlsanity.com/paper/2603.23178/) (2026)
- [Context-Aware Mutual Learning for Blind Image Inpainting and Beyond](https://mlsanity.com/paper/2609.14439/) (2026)

## Abstract (arXiv)

Digital watermark is a commonly used technique to protect the copyright of medias. Simultaneously, to increase the robustness of watermark, attacking technique, such as watermark removal, also gets the attention from the community. Previous watermark removal methods require to gain the watermark location from users or train a multi-task network to recover the background indiscriminately. However, when jointly learning, the network performs better on watermark detection than recovering the texture. Inspired by this observation and to erase the visible watermarks blindly, we propose a novel two-stage framework with a stacked attention-guided ResUNets to simulate the process of detection, removal and refinement. In the first stage, we design a multi-task network called SplitNet. It learns the basis features for three sub-tasks altogether while the task-specific features separately use multiple channel attentions. Then, with the predicted mask and coarser restored image, we design RefineNet to smooth the watermarked region with a mask-guided spatial attention. Besides network structure, the proposed algorithm also combines multiple perceptual losses for better quality both visually and numerically. We extensively evaluate our algorithm over four different datasets under various settings and the experiments show that our approach outperforms other state-of-the-art methods by a large margin. The code is available at http://github.com/vinthony/deep-blind-watermark-removal.