StegaStamp: Invisible Hyperlinks in Physical Photographs
This enables invisible hyperlinks in physical photos, potentially allowing every photo on the internet to embed unique codes, though it is incremental as it builds on existing steganography and QR code concepts.
The paper tackles the problem of embedding imperceptible digital data, specifically hyperlinks, into physical photographs using a learned steganographic algorithm, achieving robust real-time decoding of 56-bit hyperlinks from in-the-wild videos with variations in lighting and perspective.
Printed and digitally displayed photos have the ability to hide imperceptible digital data that can be accessed through internet-connected imaging systems. Another way to think about this is physical photographs that have unique QR codes invisibly embedded within them. This paper presents an architecture, algorithms, and a prototype implementation addressing this vision. Our key technical contribution is StegaStamp, a learned steganographic algorithm to enable robust encoding and decoding of arbitrary hyperlink bitstrings into photos in a manner that approaches perceptual invisibility. StegaStamp comprises a deep neural network that learns an encoding/decoding algorithm robust to image perturbations approximating the space of distortions resulting from real printing and photography. We demonstrates real-time decoding of hyperlinks in photos from in-the-wild videos that contain variation in lighting, shadows, perspective, occlusion and viewing distance. Our prototype system robustly retrieves 56 bit hyperlinks after error correction - sufficient to embed a unique code within every photo on the internet.