Image Protection for Robust Cropping Localization and Recovery
This work addresses image security for applications like forensics and media verification, though it is incremental as it builds on existing cropping detection methods by adding recovery capabilities.
The paper tackles the problem of detecting and recovering from image cropping attacks by proposing CLR-Net, a scheme that localizes cropped regions and reconstructs the original content, achieving satisfactory accuracy and image quality in experiments.
Existing image cropping detection schemes ignore that recovering the cropped-out contents can unveil the purpose of the behaved cropping attack. This paper presents \textbf{CLR}-Net, a novel image protection scheme addressing the combined challenge of image \textbf{C}ropping \textbf{L}ocalization and \textbf{R}ecovery. We first protect the original image by introducing imperceptible perturbations. Then, typical image post-processing attacks are simulated to erode the protected image. On the recipient's side, we predict the cropping mask and recover the original image. Besides, we propose a novel \textbf{F}ine-\textbf{G}rained generative \textbf{JPEG} simulator (FG-JPEG) as well as a feature alignment network to improve the real-world robustness. Comprehensive experiments prove that the quality of the recovered image and the accuracy of crop localization are both satisfactory.