yingqianwang / lf-internet Goto Github PK

Hi, how do you get the Real-World Degradation samples? It is not using bicubic downsampling method?
(2) How do you retrained the ResLF?
Thans a lot.

Thanks for sharing. When I see the codes, I can't find random flipping and 90-degree rotation in data perprocessing. And I trained the project(5×5 and upscale=4,channels=64) by myself, but my results on the test datasets are a little lower than yours(PSNR on six dataset: 29.45,30.99,37.17,31.62,30.39,31.78), but your pretrained model can get the result in this paper, so i think maybe is the problem about data augmentation(you did it but i didn't)?

Hi, author. I really appreciate your interesting work! But I would like to know which dataset is used to train the pretrained models that you provide? or you train the model with all the data in 6 datasets?

looking forward to your reply!

Hello, your work is excellent! But I have some questions, I would like to ask why L is set to 2 in the Matlab code for calculating SSIM, and should not be 1?

Do I need to convert the.mat file for the training dataset to.png?

Hi, thanks for your nice work.

It seems that both your training and testing code used the nearest downsampling instead of bicubic. Will it influence the SR performance?

Hi, I have a question to ask you. Are all the compared methods needs to retrained on the same datasets as your paper stated?
How to compute the biscubic and the SISR methods's PSNR and SSIM on one LF image?

Hope for your kindly reply,
Regards

Thanks for your sharing. I found that the images in your dataset are brighter and more comfortable than the dataset downloaded directly from the official website. How do you handle the original images, can you share the code?

When I run the evaluation.m file, I have the following problem：
错误使用 rgb2ycbcr
需要的 第 1 个输入, RGB, 应为以下类型之一:

uint8, uint16, double

但其类型是 single。

I am a beginner, what should be changed in the code?Looking forward to your reply！

Dear Yingqian,

Thanks for your work.
I download the test code and your test datasets & pretrained model. But when I run the code, The computer will crashed.
The PC is as like this: GPU: 1080Ti, 8GB memory, i7 CPU, and os is Ubuntu 18.04.
This will be happen when I run it on another PC with win7 os.
Any help about this problem?

Hello, thanks for sharing. I notice that the model is initialized using Xavier method in your paper, but I don't find correspoding code in this repo. So I'm confused and want to know why, thanks a lot! From a pytorch beginner.