Deep Robust Reversible Watermarking
This addresses the need for efficient and robust watermarking in digital media, offering a practical improvement over existing methods, though it is incremental as it builds on deep learning approaches for a specific domain.
The paper tackles the problem of robust reversible watermarking (RRW) for images, which allows perfect recovery in lossless channels and robust extraction in lossy ones, by proposing Deep Robust Reversible Watermarking (DRRW) using deep learning. It shows that DRRW outperforms state-of-the-art methods, reducing embedding, extraction, and recovery complexities by 55.14×, 5.95×, and 3.57×, respectively, and shrinking the auxiliary bitstream by 43.86×.
Robust Reversible Watermarking (RRW) enables perfect recovery of cover images and watermarks in lossless channels while ensuring robust watermark extraction in lossy channels. Existing RRW methods, mostly non-deep learning-based, face complex designs, high computational costs, and poor robustness, limiting their practical use. This paper proposes Deep Robust Reversible Watermarking (DRRW), a deep learning-based RRW scheme. DRRW uses an Integer Invertible Watermark Network (iIWN) to map integer data distributions invertibly, addressing conventional RRW limitations. Unlike traditional RRW, which needs distortion-specific designs, DRRW employs an encoder-noise layer-decoder framework for adaptive robustness via end-to-end training. In inference, cover image and watermark map to an overflowed stego image and latent variables, compressed by arithmetic coding into a bitstream embedded via reversible data hiding for lossless recovery. We introduce an overflow penalty loss to reduce pixel overflow, shortening the auxiliary bitstream while enhancing robustness and stego image quality. An adaptive weight adjustment strategy avoids manual watermark loss weighting, improving training stability and performance. Experiments show DRRW outperforms state-of-the-art RRW methods, boosting robustness and cutting embedding, extraction, and recovery complexities by 55.14\(\times\), 5.95\(\times\), and 3.57\(\times\), respectively. The auxiliary bitstream shrinks by 43.86\(\times\), with reversible embedding succeeding on 16,762 PASCAL VOC 2012 images, advancing practical RRW. DRRW exceeds irreversible robust watermarking in robustness and quality while maintaining reversibility.