This is a Pytorch implement of "MCLL-Diff: Multi-conditional Low-Light Image Enhancement based on Diffusion Probabilistic Models."
Fengxin Chen, Ye Yu*, Jun Yi, Ting Zhang, Ji Zhao, and Jun Yu (* indicates Corresponding author)
This repository contains the dataset and code for our paper.
NVM is captured in real nighttime streets with a digital camera or cell phone. It consists of 8,450 images and 63 vehicle models. The images are taken from different viewpoints, including front (F), rear (R), side (S), front-side (FS), and rear-side (RS). We name each image according to the rule of “brand_series_viewpoint_id”, where id refers to the serial number of vehicles of the same brand and series.
!!! We currently provide 100 sample images (./Images/), and all the data will be made public after accept.
Our code will be made publicly available.