Low-light image enhancement
Fig.1. Several representative examples for low/normal-light images in PNLI dataset, LOL dataset, SYN dataset and EnlightenGAN dataset. Objects and scenes captured in our PNLI dataset are more diverse, abundant and superior.
Low-light image enhancement
Compared with normal-light images, quality degradation of low-light images captured under terrible lighting conditions is serious due to inevitable environmental or technical constraints, leading to unpleasant visual perception including details degradation, color distortion, and severe noise. These phenomena have a significant impact on the performance of advanced downstream visual tasks, such as image classification, object detection, semantic segmentation [1–4], etc. To mitigate the degradation of image quality, low-light image enhancement has become an important topic in the low-level image processing community to effectively improve visual quality and restore image details.
We will use the low-light image enhancement dataset proposed by Prof. Fu’s team in [a]. They capture a Paired normal/low-light images dataset using a Canon EOS 5D Mark IV camera. The images are captured in a variety of scenes, e.g., museums, parks, streets, landscapes, vehicles, plants, buildings, symbols, and furniture. Among these images, the quantity of outdoor images is almost three times bigger than that of indoor images. It is noteworthy that all the scenes in their dataset are static to ensure that the content of the low-light image and its ground-truth are identical. We will host the competition using open source online platform, e.g. CodaLab. All submissions are evaluated by our script running on the server and we will double check the results of top-rank methods manually before releasing the final test-set rating.