lolblur

[Yolo1-gguo]

Hello, could you please explain the difference between low_blur_noise and low_blur in the training dataset? When training, we treat low_sharp as the ground truth, and the input can be either low_blur_noise or low_blur, correct? Another question is about the role of high_sharp_scaled and high_sharp_original. Could you clarify their purposes?Thanks!!!!!!