RealBasicVSR

RealBasicVSR copied to clipboard

What is GT when training RealBasicVSR

1

Because RealBasicVSR is evaluate by non-reference metric (NIQE, PI), what is the GT or loss used for training RealBasicVSR?

DachunKai

I have a low-quality, low-resolution video, such as a CCTV camera recording in a dark and blurry environment. After processing it with a pre-trained model, the quality of the output...

chouti

Thanks for your excellent work, I've got a problem when training with only one GPU, could you please give me some guidance on non-distributed learning commands, thank you. THE logs...

Xiao-R-Y

Why put the code in such a poor framework? If the framework is changed today and tomorrow, the model will not run at all.

xihao-1223

Hi, Does the released pretrained model support x2 superresolution?

Pixie8888

The training completes the first stage，when tested on REDS data set, abnormal color appears, GT:  SR image:  please,in first stage,have you ever been in the same situation?

sunyclj

about VideoLQ dataset

1

In VideoLQ datasets, there are only low-quality LQ images，none HR images. How can it be used as a test?

sunyclj

I want to train x2 model. So, I revised code of 'realbasicvsr_wogon_c~.py' in configs folder. Specifically, I changed scale parameter from 4 to 2 and tried training. Inference was made...

sunghyun1215

Nothing too complicated, updated inference code to work out of the box for mmagic + mmcv2.0 since the MMinferencer from mmagic wasn't really working as intended out of the box....

jere357

Hi! I notice that the training process only needs the train_sharp videos in REDS dataset, the low-quality video inputs are automatically generated in the training pipeline. My question is how...

JingYansen