Abstract

Steganography finds its use in visual medium such as providing metadata and watermarking. With support of efficient latent representations and foveated rendering, we trained models that improve existing capacity limits from 100 to 500 bits, while achieving better accuracy of up to 1 failure bit out of 2000, at 200K test bits. Finally, we achieve a comparable visual quality of 31.47 dB PSNR and 0.13 LPIPS, showing the effectiveness of novel perceptual design in creating multi-modal latent representations in steganography.

Affiliated Institutions

Related Publications

Publication Info

Year
2025
Type
preprint
Pages
1-2
Citations
0
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

0
OpenAlex

Cite This

Lin Li, Henry Kam, Qi Sun et al. (2025). Foveation Improves Payload Capacity in Steganography. , 1-2. https://doi.org/10.1145/3757374.3771423

Identifiers

DOI
10.1145/3757374.3771423