使用本地化訊息為任何內容加上浮水印

摘要

圖像浮水印方法並非針對處理小型浮水印區域而設計。這限制了在現實世界情境中應用的可能性，因為圖像的部分可能來自不同來源或已經編輯過。我們引入了一個用於局部圖像浮水印的深度學習模型，名為Watermark Anything Model（WAM）。WAM嵌入器在不可察覺地修改輸入圖像，而提取器將接收到的圖像分割為帶有浮水印和無浮水印的區域，並從被識別為帶有浮水印的區域中恢復一個或多個隱藏訊息。這些模型在低解析度下聯合訓練，並且不受感知約束，然後進行後訓練以實現不可察覺性和多重浮水印。實驗表明，WAM在不可察覺性和穩健性方面與最先進的方法相當競爭，尤其是對抗修補和拼貼，即使在高解析度圖像上也是如此。此外，它還提供了新的功能：WAM能夠在拼貼圖像中定位帶有浮水印的區域，並從多個小區域中提取出不超過圖像表面的10％的獨特32位元訊息，即使對於小型的256x256圖像也是如此。

English

Image watermarking methods are not tailored to handle small watermarked areas. This restricts applications in real-world scenarios where parts of the image may come from different sources or have been edited. We introduce a deep-learning model for localized image watermarking, dubbed the Watermark Anything Model (WAM). The WAM embedder imperceptibly modifies the input image, while the extractor segments the received image into watermarked and non-watermarked areas and recovers one or several hidden messages from the areas found to be watermarked. The models are jointly trained at low resolution and without perceptual constraints, then post-trained for imperceptibility and multiple watermarks. Experiments show that WAM is competitive with state-of-the art methods in terms of imperceptibility and robustness, especially against inpainting and splicing, even on high-resolution images. Moreover, it offers new capabilities: WAM can locate watermarked areas in spliced images and extract distinct 32-bit messages with less than 1 bit error from multiple small regions - no larger than 10% of the image surface - even for small 256times 256 images.

使用本地化訊息為任何內容加上浮水印

Watermark Anything with Localized Messages

摘要

Summary

Support