Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915231538610176 |
|---|---|
| author | Leng, Yicheng Fang, Chaowei Chen, Junye Fang, Yixiang Li, Sheng Li, Guanbin |
| author_facet | Leng, Yicheng Fang, Chaowei Chen, Junye Fang, Yixiang Li, Sheng Li, Guanbin |
| contents | Visible watermark removal which involves watermark cleaning and background content restoration is pivotal to evaluate the resilience of watermarks. Existing deep neural network (DNN)-based models still struggle with large-area watermarks and are overly dependent on the quality of watermark mask prediction. To overcome these challenges, we introduce a novel feature adapting framework that leverages the representation modeling capacity of a pre-trained image inpainting model. Our approach bridges the knowledge gap between image inpainting and watermark removal by fusing information of the residual background content beneath watermarks into the inpainting backbone model. We establish a dual-branch system to capture and embed features from the residual background content, which are merged into intermediate features of the inpainting backbone model via gated feature fusion modules. Moreover, for relieving the dependence on high-quality watermark masks, we introduce a new training paradigm by utilizing coarse watermark masks to guide the inference process. This contributes to a visible image removal model which is insensitive to the quality of watermark mask during testing. Extensive experiments on both a large-scale synthesized dataset and a real-world dataset demonstrate that our approach significantly outperforms existing state-of-the-art methods. The source code is available in the supplementary materials. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04687 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal Leng, Yicheng Fang, Chaowei Chen, Junye Fang, Yixiang Li, Sheng Li, Guanbin Computer Vision and Pattern Recognition Artificial Intelligence Multimedia Image and Video Processing I.2.10; I.4.4; I.4.5 Visible watermark removal which involves watermark cleaning and background content restoration is pivotal to evaluate the resilience of watermarks. Existing deep neural network (DNN)-based models still struggle with large-area watermarks and are overly dependent on the quality of watermark mask prediction. To overcome these challenges, we introduce a novel feature adapting framework that leverages the representation modeling capacity of a pre-trained image inpainting model. Our approach bridges the knowledge gap between image inpainting and watermark removal by fusing information of the residual background content beneath watermarks into the inpainting backbone model. We establish a dual-branch system to capture and embed features from the residual background content, which are merged into intermediate features of the inpainting backbone model via gated feature fusion modules. Moreover, for relieving the dependence on high-quality watermark masks, we introduce a new training paradigm by utilizing coarse watermark masks to guide the inference process. This contributes to a visible image removal model which is insensitive to the quality of watermark mask during testing. Extensive experiments on both a large-scale synthesized dataset and a real-world dataset demonstrate that our approach significantly outperforms existing state-of-the-art methods. The source code is available in the supplementary materials. |
| title | Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Multimedia Image and Video Processing I.2.10; I.4.4; I.4.5 |
| url | https://arxiv.org/abs/2504.04687 |