Closed bjiale closed 2 years ago
That’s strange. Can you send me the input you used and let me have a try?
My input data. tractor.zip thanks~
How did you add the noise? Also, I observed pixel shift when compared with the GT.
I used the RandomNoise function in your code to add the noise.
About the pixel shift, I crop 2 pixels in width to make the image size can divided by 4.
Is my data's noise type different from the training dataset?
I guess that's because you saved the frames as .jpg
, which produces compression. Try saving it to .png
.
In addition, For frames not divisible by 4, I padded zero at the end (i.e., last rows and columns) and crop it after processing, to make sure there is no pixel shift.
Yes, thank you~ You are right. I try to use png format image and it works!
Hi @ckkelvinchan , I have tried to run the denoise pretrianed model with DAVIS-test dataset, but the result images has no difference between the input images. My experiment is as below: pretrained model: basicvsr_plusplus_denoise-28f6920c.pth optical flow model: I download it to my local path dataset: I use the the tractor folder in DAIVS-test dataset which is used in your paper. I add the sigma 50 gaussian noise to the pictures as input. result:![image](https://user-images.githubusercontent.com/106739374/171635832-e6c8cf29-fd16-4202-8839-00fe2d24c290.png)
It seem that it run successfully, but the result has no change between the input. Is their any parameter or option error in my attempt? By the way, basicvsr_plusplus_c64n7_8x1_600k_reds4.pth can run successfully and the result is excellent!