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

请问SDSD的static version和原本的SDSD有什么区别 #13

Open ciki000 opened 1 year ago

ciki000 commented 1 year ago

Different from original SDSD datasets with dynamic scenes, we utilize its static version (the scenes are the same of original SDSD) 这里的dynamic 和static version的区别是什么? 另外SDSD_indoor的百度网盘验证码似乎是不正确的

xiaogang00 commented 1 year ago

As indicated in the paper of SDSD, there is one phase during the data collection, when the camera has no motion. During this phase, the collected data serves as SDSD-static. This is similar to the data collection strategy of SID. The baidu pan password for SDSD_indoor is correct when I test. If you can not download from baidu pan, please consider using google pan.