# WDNet: Watermark-Decomposition Network for Visible Watermark Removal

arXiv: https://arxiv.org/abs/2012.07616 · HTML: https://mlsanity.com/paper/2012.07616/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2020.

## Built on by (most cited first, 30 of 37)

- [InstructDiffusion: A Generalist Modeling Interface for Vision Tasks](https://mlsanity.com/paper/2309.03895/) (2023)
- [Invisible Image Watermarks Are Provably Removable Using Generative AI](https://mlsanity.com/paper/2306.01953/) (2023)
- [I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing](https://mlsanity.com/paper/2408.14180/) (2024)
- [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)
- [PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions](https://mlsanity.com/paper/2409.15278/) (2024)
- [Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data](https://mlsanity.com/paper/2511.12609/) (2025)
- [Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal](https://mlsanity.com/paper/2207.08178/) (2022)
- [Blind Image Decomposition](https://mlsanity.com/paper/2108.11364/) (2021)
- [Visible Watermark Removal via Self-calibrated Localization and Background Refinement](https://mlsanity.com/paper/2108.03581/) (2021)
- [Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision](https://mlsanity.com/paper/2504.04903/) (2025)
- [Warfare:Breaking the Watermark Protection of AI-Generated Content](https://mlsanity.com/paper/2310.07726/) (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)
- [ConText: Driving In-context Learning for Text Removal and Segmentation](https://mlsanity.com/paper/2506.03799/) (2025)
- [Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal](https://mlsanity.com/paper/2312.14383/) (2023)
- [Strong and Controllable Blind Image Decomposition](https://mlsanity.com/paper/2403.10520/) (2024)
- [Dataset Ownership Verification for Pre-trained Masked Models](https://mlsanity.com/paper/2507.12022/) (2025)
- [SpecGuard: Spectral Projection-based Advanced Invisible Watermarking](https://mlsanity.com/paper/2510.07302/) (2025)
- [Can Protective Watermarking Safeguard the Copyright of 3D Gaussian Splatting?](https://mlsanity.com/paper/2511.22262/) (2025)
- [Preventing Unauthorized AI Over-Analysis by Medical Image Adversarial Watermarking](https://mlsanity.com/paper/2303.09858/) (2023)
- [LayeredDoc: Domain Adaptive Document Restoration with a Layer Separation Approach](https://mlsanity.com/paper/2406.08610/) (2024)
- [ArtiFade: Learning to Generate High-quality Subject from Blemished Images](https://mlsanity.com/paper/2409.03745/) (2024)
- [Spread them Apart: Towards Robust Watermarking of Generated Content](https://mlsanity.com/paper/2502.07845/) (2025)
- [AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective](https://mlsanity.com/paper/2603.24857/) (2026)
- [Mask-Guided Image Person Removal with Data Synthesis](https://mlsanity.com/paper/2209.14890/) (2022)
- [Visual Watermark Removal Based on Deep Learning](https://mlsanity.com/paper/2302.11338/) (2023)
- [AURA : Automatic Mask Generator using Randomized Input Sampling for Object Removal](https://mlsanity.com/paper/2305.07857/) (2023)
- [Image background assessment as a novel technique for insect microhabitat identification](https://mlsanity.com/paper/2305.18207/) (2023)
- [WMFormer++: Nested Transformer for Visible Watermark Removal via Implict Joint Learning](https://mlsanity.com/paper/2308.10195/) (2023)

## Abstract (arXiv)

Visible watermarks are widely-used in images to protect copyright ownership. Analyzing watermark removal helps to reinforce the anti-attack techniques in an adversarial way. Current removal methods normally leverage image-to-image translation techniques. Nevertheless, the uncertainty of the size, shape, color and transparency of the watermarks set a huge barrier for these methods. To combat this, we combine traditional watermarked image decomposition into a two-stage generator, called Watermark-Decomposition Network (WDNet), where the first stage predicts a rough decomposition from the whole watermarked image and the second stage specifically centers on the watermarked area to refine the removal results. The decomposition formulation enables WDNet to separate watermarks from the images rather than simply removing them. We further show that these separated watermarks can serve as extra nutrients for building a larger training dataset and further improving removal performance. Besides, we construct a large-scale dataset named CLWD, which mainly contains colored watermarks, to fill the vacuum of colored watermark removal dataset. Extensive experiments on the public gray-scale dataset LVW and CLWD consistently show that the proposed WDNet outperforms the state-of-the-art approaches both in accuracy and efficiency. The code and CLWD dataset are publicly available at https://github.com/MRUIL/WDNet.