search

Reyhanehne / CVF-SID_PyTorch

Official implementation of the paper "CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from Image" (CVPR 2022)
70 stars 11 forks source link

why we need groung truth? #6

Open lulu-165 opened 1 year ago

lulu-165 commented 1 year ago

Hello, I would like to ask, why it is mentioned in the paper that we do not need a clean image for self-supervised denoising, but the ground truth is required in the code？

Reyhanehne commented 1 year ago

Hello, The ground truth data are only needed for evaluation in the test phase, and we do not need the GT images for training.

lulu-165 commented 1 year ago

I see, thank you!