paper-with-me

홈 › Papers

SSH-Net: A Self-Supervised and Hybrid Network for Noisy Image Watermark Removal

2025-05-08 · Wenyang Liu, Jianjun Gao, Kim-Hui Yap

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.

📄 PDF Abstract BibTeX arXiv:2505.05088

Code (1)

wenyang001/ssh-net 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Perceptive self-supervised learning network for noisy image watermark removal

2024-03-04 · Chunwei Tian, Menghua Zheng, Bo Li, Yanning Zhang 외

Popular methods usually use a degradation model in a supervised way to learn a watermark removal model. However, it is true that reference images are difficult to obtain in the real world, as well as collected images by …

Self-Supervised Learning

A self-supervised CNN for image watermark removal

2024-03-09 · Chunwei Tian, Menghua Zheng, Tiancai Jiao, WangMeng Zuo 외

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…

Watermarking Images in Self-Supervised Latent Spaces

2021-12-17 · Pierre Fernandez, Alexandre Sablayrolles, Teddy Furon, Hervé Jégou 외

We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches. We present a way to embed both marks and binary messages into their latent spaces, leveraging data augmen…

Data AugmentationDecoder

Npix2Cpix: A GAN-Based Image-to-Image Translation Network With Retrieval- Classification Integration for Watermark Retrieval From Historical Document Images

2024-06-05 · Utsab Saha, Sawradip Saha, Shaikh Anowarul Fattah, Mohammad Saquib

The identification and restoration of ancient watermarks have long been a major topic in codicology and history. Classifying historical documents based on watermarks is challenging due to their diversity, noisy samples, …

Generative Adversarial NetworkImage-to-Image TranslationOne-Shot LearningRetrieval+1

Hybrid Learning: A Novel Combination of Self-Supervised and Supervised Learning for MRI Reconstruction without High-Quality Training Reference

2025-05-09 · Haoyang Pei, Ding Xia, Xiang Xu, William Moore 외

Purpose: Deep learning has demonstrated strong potential for MRI reconstruction, but conventional supervised learning methods require high-quality reference images, which are often unavailable in practice. Self-supervise…

Image ReconstructionMRI ReconstructionSelf-Supervised LearningSSIM