search

dvlab-research / SNR-Aware-Low-Light-Enhance

This is the official implementation for the paper "SNR-aware low-light image enhancement" in CVPR2022
168 stars 20 forks source link

Train and Test datasets #4

Open siyv6 opened 1 year ago

siyv6 commented 1 year ago

Hello author, it is a great honor to see your work. I would like to ask you some questions about the use of the data set, that is, the SMID data set I downloaded contains 202 pictures of SMID_Long_png and 20809 pictures of SMID_LQ_png. How to divide the training set and the test set？and how about SID ?

xiaogang00 commented 1 year ago

Hello: In the collection of SMID, the low-light images are collected by short exposure with different times, and the corresponding normal-light image is obtained by long exposure. Thus, in the dataset of SMID, one normal-light image can be the ground truth of the corresponding several low-light images. This is why the number of low-light image and normal-light image is different. The similar situation is also applicable to the SID dataset.

wangchx67 commented 1 year ago

Hi, I want to know how to divide the training data and testing data in SMID, SDSD and SID, which means the number of training data and testing data.