hanna-xu / u2fusion Goto Github PK

请问作者，运行代码的各种包的版本可否提供，配置环境很多报错，如能提供，非常感谢

本人在写论文，要与U2fusion做对比，直接把model文件夹里的模型用在本人的自建数据集上，是否可以作为论文中U2fusion模型的融合结果

你好，请问训练的图片通道数必须为1嘛？ 还有test的时候，可以输入通道数为4的图像嘛？

output = ycbcr2rgb(output, img2_cb, img2_cr)，我怎么没有看见定义的img2_cb, img2_cr

Thanks for the nice work! I have a question regarding fusing multiple images. The paper mentions fusing multiple images sequentially (two at a time.)

But it appears to me that the loss used for training can be easiliy generalized to more than two images and hence achieving multiple-image (more than two images) fusion as one single pass to the DenseNet. Am I right or do I miss something?

Thanks!

Hi, Han Xu

Thank you for your excellent work!

In this work, is the image after the fusion of the two LDR images still 8bit? 12bit or higher.

Thank you!

作者您好，我对U2Fusion的思路很感兴趣，想先试试自己的数据集训练效果，不过看到train_task.py中没有定义main函数，请问方便的话可以提供一下对应的训练代码吗？

Hi, Han Xu

You can provide the papers' RFNet: Unsupervised Network for Mutually Reinforcing Multi - modal Image Registration and Fusion 'code?

Thank you!

您好 我想引用您的论文，但是为什么test出来的效果都是黑色，请问什么原因如何解决呢非常感谢

Hi,
Thank your great contributio for this community.
Recently, I read this paper "RFNet: Unsupervised Network for Mutually Reinforcing Multi-modal Image Registration and Fusion"
Is there any plan for the open-source code of RF-Net?
Or could you share this code with me. Appreciate it!

在更换自己的数据集后（MSRS，LLVIP），测试结果的图片会出现大面积的雪花而不是清晰的图片

我正在学习1通道的红外+3通道的RGB图像的融合，您的论文中提到对RGB使用YCbCr转换，只用Y分量去融合，请问是如何实现的？

hi, thank you for sharing your code. I have some questions for you.

are the medical dataset used when training on task1? It seems that the datasets you provide did not include the medical dataset, and the dataset did not seems to be used in your code. if used, could you please provide a link to download it and update the code to use it? looking forward to an early reply, thank you.

Hi, vgg16.npy file is not downloading. Can you please share the file in GitHub?