vvictoryuki / cross Goto Github PK
View Code? Open in Web Editor NEW[NeurIPS 2023] Official PyTorch implementation for the paper "CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography"
[NeurIPS 2023] Official PyTorch implementation for the paper "CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography"
您好,我是来自北京邮电大学的一名博士生,看来您的论文,我非常受启发,感觉您提出了一个隐写术的新方向,原始的隐写术要求嵌入信息要小于载体,您这种无载体的隐写术可以使得嵌入信息与容器图像大小相同。
我有个问题,您给的requirements.txt中的库我都下不到,我试了好几个镜像都不行,请您给我一个镜像或下载地址好吗,感激不尽。
作者您好,我现在在读研一,我不太清楚结果分析的流程,我想看一下您用于分析结果的代码,谢谢。
`
latent_noise = ode.invert(prompt_1, image_gt_latent, is_forward=True)
image_hide_latent = ode.invert(prompt_2, latent_noise, is_forward=False)
# save container image
image_hide = ode.latent2image(image_hide_latent)
cv2.imwrite("{:s}/hide.png".format(args.save_path), cv2.cvtColor(image_hide, cv2.COLOR_RGB2BGR))
# reveal process
latent_noise = ode.invert(rev_prompt_2, image_hide_latent, is_forward=True)
image_reverse_latent = ode.invert(rev_prompt_1, latent_noise, is_forward=False)
image_reverse = ode.latent2image(image_reverse_latent)`
`
In this piece of code, it seems like you are directly using the latent vector (1*4*64*64) that has not gone through vae.decoder for secret message extraction. In the concept of image steganography, we should use the image generated after vae.decoder (e.g. 1*3*512*512) as the secret message container.
As in the following code:
`
latent_noise = ode.invert(prompt_1, image_gt_latent, is_forward=True)
image_hide_latent = ode.invert(prompt_2, latent_noise, is_forward=False)
# save container image
image_hide = ode.latent2image(image_hide_latent)
cv2.imwrite("{:s}/hide.png".format(args.save_path), cv2.cvtColor(image_hide, cv2.COLOR_RGB2BGR))
hide_latent_for_reveal = ode.image2latent(image_hide)
# reveal process
latent_noise = ode.invert(rev_prompt_2, hide_latent_for_reveal, is_forward=True)
image_reverse_latent = ode.invert(rev_prompt_1, latent_noise, is_forward=False)
image_reverse = ode.latent2image(image_reverse_latent)`
`
I have read your paper and I am curious about the dataset Stego260.I want to use your model using different methods to hide two images,but I don't see any access to the dataset.Could you please offer it?Thanks a lot.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.