astra-vision / manifest Goto Github PK

Hi, authors!

Thanks for your excellent work. I would like to know how long it takes to train your model on a single GPU (e.g., 3090Ti).

Besides, I would like to know if you have tested the inference speed and FLOPs on high-resolution (e.g., 2k) images. How is your computational efficiency compared with the previous state-of-the-art?

Hello, sorry for disturbing you!

I saw some details in the article that will be presented in the supplementary materials, but I did not find them on the internet. Therefore, I would like to request that you provide the supplementary materials for this article.

I‘m much obliged to you for helping me.

Very solid work！I have some questions，

1.How to train our own dataset？Can you give some examples? Or a training script? For example, we have some normal images and some foggy images. How to train them?

2.If we only have a 2080TI GPU, can we finish the training?

Thank you.

Can this method only be used for image style conversion between day and night?Can it be used to generate fog scenes?