StegaStamp: Invisible Hyperlinks in Physical Photographs

Tancik, Matthew; Mildenhall, Ben; Ng, Ren

doi:10.1109/cvpr42600.2020.00219

Cited by 222 publications

(175 citation statements)

References 30 publications

Supporting

Mentioning

155

Contrasting

Order By: Relevance

“…However, none of these methods account for the localization problem of encoded messages in input images. Recently, Stegastamp [Tancik et al 2020] starts to include perspective warp to the perturbation pipeline. However, their detection method presents a degraded performance in the real experiments due to the separate architecture of the segmentation network.…”

Section: Related Workmentioning

confidence: 99%

DeepFormableTag

et al. 2021

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

DeepFormableTag

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Various methods have been proposed for image watermarking that are mostly robust to conventional image attacks [ 1 , 2 , 3 ] but are vulnerable to multiple attacks. These schemes are not typically designed to work for screen-capture photos, but in recent years, print-to-scan [ 4 , 5 ], print-to-capture [ 6 , 7 ], and screenshot [ 8 ] scenarios have been studied extensively. However, screen-shooting requires more sophisticated and new attacks, such as moiré, different scale display, lens distortion, and light source distortion.…”

Section: Introductionmentioning

confidence: 99%

Screen-Shooting Resilient Watermarking Scheme via Learned Invariant Keypoints and QT

Bai

Zhang

et al. 2021

Sensors

View full text Add to dashboard Cite

This paper proposes a screen-shooting resilient watermarking scheme via learned invariant keypoints and QT; that is, if the watermarked image is displayed on the screen and captured by a camera, the watermark can be still extracted from the photo. A screen-shooting resilient watermarking algorithm should meet the following two basic requirements: robust keypoints and a robust watermark algorithm. In our case, we embedded watermarks by combining the feature region filtering model to SuperPoint (FRFS) neural networks, quaternion discrete Fourier transform (QDFT), and tensor decomposition (TD). First we applied FRFS to locate the embedding feature regions which are decided by the keypoints that survive screen-shooting. Second, we structured watermark embedding regions centered at keypoints. Third, the watermarks were embedded by the QDFT and TD (QT) algorithm, which is robust for capturing process attacks. In a partial shooting scenario, the watermark is repeatedly embedded into different regions in an image to enhance robustness. Finally, we extracted the watermarks from at least one region at the extraction stage. The experimental results showed that the proposed scheme is very robust for camera shooting (including partial shooting) different shooting scenarios, and special attacks. Moreover, the efficient mechanism of screen-shooting resilient watermarking could have propietary protection and leak tracing applications.

show abstract

“…Fueled by the powerful learning ability of Deep Neural Networks (DNN), researchers have applied it to watermarking and achieved excellent performance [18][19][20]. However, these methods usually suffer from the following problems: 1) Single model is often not universal for different image resolutions or various embedding capacities [18,20]. 2) These models often do not consider the robustness against various attacks and the applicability is not satisfactory [19].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Flexible 3D Histogram Watermarking

Chen

Liu

Cui

et al. 2021

2021 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

Watermarking technology has attracted increasing attentions in the past few years, and a great deal traditional and deep learning-based methods have been proposed. However, these methods usually suffer from the following three challenges: First, the current algorithms are designed separately for images or videos, and there is no universal solution. Second, most algorithms cannot resist screen recording, which limits its application. Third, some algorithms can only embed fixedlength watermarks and cannot handle the embedding capacity flexibly. In this paper, a novel watermarking scheme is proposed based on spatial and temporal histograms, in which two types of histogram watermarking are designed: One is constructed in the spatial domain, using the low-frequency characteristics of the image to change the shape of the histogram and embed the watermark. The other is established in the time domain, which uses the similarity of adjacent frames and combines texture features to modify the shape of the temporal histogram to embed the watermark. Experimental results compared with the state-of-the-art demonstrate that the proposed scheme achieves superior performance.

show abstract

StegaStamp: Invisible Hyperlinks in Physical Photographs

Cited by 222 publications

References 30 publications

DeepFormableTag

DeepFormableTag

Screen-Shooting Resilient Watermarking Scheme via Learned Invariant Keypoints and QT

Adaptive Flexible 3D Histogram Watermarking

Contact Info

Product

Resources

About