注视点增强隐写术的载荷能力
Foveation Improves Payload Capacity in Steganography
AI总结:
通过高效潜在表示和注视点渲染,提升隐写术的载荷能力至500位,并在高准确率和视觉质量上取得显著成果。
摘要:
隐写术在视觉媒介中用于提供元数据和水印。借助高效的潜在表示和注视点渲染,我们训练了模型,将现有容量限制从100提升到500位,同时在200,000个测试位中达到最高2000位中仅1位失败的准确率。最终,我们实现了31.47 dB PSNR和0.13 LPIPS的可比视觉质量,展示了新颖的感知设计在隐写术中创建多模态潜在表示的有效性。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。