TL;DR
This paper introduces MBRS, a novel deep learning watermarking framework that significantly improves robustness against JPEG compression and other distortions by using a mini-batch training approach with real and simulated JPEGs, along with advanced feature learning techniques.
Contribution
The paper proposes a new end-to-end training architecture utilizing mini-batches of real and simulated JPEG compression to enhance robustness, along with novel network components like Squeeze-and-Excitation blocks and a message processor.
Findings
Achieves less than 0.01% bit error rate under JPEG Q=50
Maintains PSNR above 36 for encoded images
Demonstrates robustness against various distortions
Abstract
Based on the powerful feature extraction ability of deep learning architecture, recently, deep-learning based watermarking algorithms have been widely studied. The basic framework of such algorithm is the auto-encoder like end-to-end architecture with an encoder, a noise layer and a decoder. The key to guarantee robustness is the adversarial training with the differential noise layer. However, we found that none of the existing framework can well ensure the robustness against JPEG compression, which is non-differential but is an essential and important image processing operation. To address such limitations, we proposed a novel end-to-end training architecture, which utilizes Mini-Batch of Real and Simulated JPEG compression (MBRS) to enhance the JPEG robustness. Precisely, for different mini-batches, we randomly choose one of real JPEG, simulated JPEG and noise-free layer as the noise…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsDiffusion
