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

TL;DR

SSH-Net introduces a self-supervised, hybrid CNN-Transformer architecture for effective noisy image watermark removal without requiring paired datasets, leveraging a dual-network design and shared feature encoder.

Contribution

The paper presents SSH-Net, a novel self-supervised hybrid network that removes watermarks and noise from images without needing paired training data, combining CNNs and Transformers.

Findings

Effective watermark removal in noisy images demonstrated.

Self-supervised training reduces dependency on paired datasets.

Hybrid architecture improves performance over existing methods.

Abstract

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.