无需配对数据，自监督去除含噪图像中的可见水印
SSH-Net: A Self-Supervised and Hybrid Network for Noisy Image Watermark Removal
- 自监督生成无水印参考图，避免依赖真实配对数据
- 双网络结构：轻量CNN去噪 + Transformer主网络去水印与噪声
- 适合真实场景中水印去除，尤其适用于无标注数据环境
可见水印去除因图像固有复杂性及携带的噪声而极具挑战。现有方法多依赖需成对水印图像与无水印图像的监督学习，但此类数据在真实场景中难以获取。为此，我们提出SSH-Net——一种专为含噪图像水印去除设计的自监督混合网络。SSH-Net通过自监督方式利用水印分布合成参考无水印图像，并采用双网络架构完成任务：上层网络专注于简单去噪，采用轻量级CNN；下层网络则处理更复杂的水印与噪声联合去除任务，引入Transformer块以建模长程依赖并捕捉精细图像特征。为提升模型性能，我们在双网络前引入共享的CNN特征编码器，提取可被两网络共用的通用特征。代码将开源于https://github.com/wenyang001/SSH-Net。
原文摘要 · Abstract (English)
Visible watermark removal is challenging due to its inherent complexities and the noise carried within images. Existing methods primarily rely on supervised learning approaches that require paired datasets of watermarked and watermark-free images, which are often impractical to obtain in real-world scenarios. To address this challenge, we propose SSH-Net, a Self-Supervised and Hybrid Network specifically designed for noisy image watermark removal. SSH-Net synthesizes reference watermark-free images using the watermark distribution in a self-supervised manner and adopts a dual-network design to address the task. The upper network, focused on the simpler task of noise removal, employs a lightweight CNN-based architecture, while the lower network, designed to handle the more complex task of simultaneously removing watermarks and noise, incorporates Transformer blocks to model long-range dependencies and capture intricate image features. To enhance the model's effectiveness, a shared CNN-based feature encoder is introduced before dual networks to extract common features that both networks can leverage. Our code will be available at https://github.com/wenyang001/SSH-Net.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。