Aparecium: Revealing Secrets from Physical Photographs

TL;DR

Aparecium is a deep learning-based watermarking framework that robustly encodes and retrieves watermarks from physical photographs under complex distortions like folding, bending, and shooting from various angles.

Contribution

The paper introduces Aparecium, a novel deep watermarking method that handles complex physical distortions and irregular shapes, surpassing limitations of existing solutions.

Findings

Robust against digital and physical distortions including folding and bending

Effective at long-distance and large-angle photography

Maintains high visual quality of watermarked images

Abstract

Watermarking is a crucial tool for safeguarding copyrights and can serve as a more aesthetically pleasing alternative to QR codes. In recent years, watermarking methods based on deep learning have proved superior robustness against complex physical distortions than traditional watermarking methods. However, they have certain limitations that render them less effective in practice. For instance, current solutions necessitate physical photographs to be rectangular for accurate localization, cannot handle physical bending or folding, and require the hidden area to be completely captured at a close distance and small angle. To overcome these challenges, we propose a novel deep watermarking framework dubbed \textit{Aparecium}. Specifically, we preprocess secrets (i.e., watermarks) into a pattern and then embed it into the cover image, which is symmetrical to the final decoding-then-extracting process. To capture the watermarked region from complex physical scenarios, a locator is also introduced. Besides, we adopt a three-stage training strategy for training convergence. Extensive experiments demonstrate that \textit{Aparecium} is not only robust against different digital distortions, but also can resist various physical distortions, such as screen-shooting and printing-shooting, even in severe cases including different shapes, curvature, folding, incompleteness, long distances, and big angles while maintaining high visual quality. Furthermore, some ablation studies are also conducted to verify our design.