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.

We are developing an app that scans a normal-looking photo and gets the information in it, such as the price of goods in a mall, details of objects in a museum, 2D pictures to a VR view. Now there is a demo:

GitHub: @ScanCan

✨ Features:

• Multiple scenes
• Social interest
• User Data Privacy
• Wireless simultaneous interpretation
• Deep 3D scene fusion
• AR-DAO Decentralized DAO community

Oblique Angles	Variable Lighting	Occlusion	Reflections

Processing

Sponsorship would help make it more sustainable for me to work on more open source projects and maintain them, so it is greatly appreciated! Note that the tiers are for sponsorship only - if you'd like to discuss any sort of opportunity, feel free to contact me.

Thanks! 💜

如果您来自中国区，建议通过微信/支付宝赞助！

☎️ Contact me