I encountered severe artifact when testing on VID4 with pretrained model
T5eng opened this issue · 6 comments
as described in the title, here is some cases. But case calendar is alright, same as visual quality in the paper.
It would be great if you could help solve this problem.
The released model is for BI setting. It means that you need to use Matlab resize function with the "bicubic" option to downsample HR frames to generate LR frames.
In my experiment, LR frames are generated with cv2.resize(... , interpolation=cv2.INTER_CUBIC) and frames in calendar set are all looking good. Artifact exists only in foliage, city and walk set... so weird...
The functions in OpenCV and Matlab should be different. I guess you will have the similar issue if you test the generated LR frames using other BI models. But, I also cannot understand why the results of the calendar sequence are good.
I tried to generate LR with Matlab bicubic interpolation. But artifact still exists.....
Could you use this code: https://github.com/yulunzhang/RDN/blob/master/RDN_IR/RDN_TestCode/RDN_SR_RGB/Prepare_TestData_HR_LR.m? The BI setting.
It works. It seems this and some other similar methods are functioning on very specifically degredation....