Foveation Improves Payload Capacity in Steganography

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lin, Lifeng Qiu, Kam, Henry, Sun, Qi, Akşit, Kaan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912756653883392
author Lin, Lifeng Qiu
Kam, Henry
Sun, Qi
Akşit, Kaan
author_facet Lin, Lifeng Qiu
Kam, Henry
Sun, Qi
Akşit, Kaan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13151
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Foveation Improves Payload Capacity in Steganography
Lin, Lifeng Qiu
Kam, Henry
Sun, Qi
Akşit, Kaan
Computer Vision and Pattern Recognition
Graphics
I.2.10; I.4
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.
title Foveation Improves Payload Capacity in Steganography
topic Computer Vision and Pattern Recognition
Graphics
I.2.10; I.4
url https://arxiv.org/abs/2510.13151