google-research / maxim

[CVPR 2022 Oral] Official repository for "MAXIM: Multi-Axis MLP for Image Processing". SOTA for denoising, deblurring, deraining, dehazing, and enhancement.

Home Page:https://arxiv.org/abs/2201.02973

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

question about RESIDE-Outdoor

YuZheng9 opened this issue · comments

Thank you for your work!

I have a little question. There are two versions of the RESIDE-outdoor dataset. RESIDE:V0 and RESIDE-β.

RESIDE:V0 has 313,950 synthetic hazy images.
RESIDE-β has 72135 synthetic hazy images.

Which version of RESIDE-outdoor dataset did you use to train and get the results in the paper?

Thank you and look forward to your reply.

We used RESIDE:V0 (313k), as shown in Table 8 of https://arxiv.org/pdf/2201.02973.pdf