Foveation Improves Payload Capacity in Steganography
This work addresses the need for higher capacity and accuracy in steganography for applications like metadata embedding and watermarking, representing a strong specific gain rather than a broad breakthrough.
The paper tackled the problem of limited payload capacity in steganography by using foveated rendering and latent representations, increasing capacity from 100 to 500 bits while achieving high accuracy with only 1 failure bit out of 2000 and maintaining visual quality at 31.47 dB PSNR and 0.13 LPIPS.
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.