Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Low-Light Video Enhancement with Synthetic Event Guidance

About

Low-light video enhancement (LLVE) is an important yet challenging task with many applications such as photographing and autonomous driving. Unlike single image low-light enhancement, most LLVE methods utilize temporal information from adjacent frames to restore the color and remove the noise of the target frame. However, these algorithms, based on the framework of multi-frame alignment and enhancement, may produce multi-frame fusion artifacts when encountering extreme low light or fast motion. In this paper, inspired by the low latency and high dynamic range of events, we use synthetic events from multiple frames to guide the enhancement and restoration of low-light videos. Our method contains three stages: 1) event synthesis and enhancement, 2) event and image fusion, and 3) low-light enhancement. In this framework, we design two novel modules (event-image fusion transform and event-guided dual branch) for the second and third stages, respectively. Extensive experiments show that our method outperforms existing low-light video or single image enhancement approaches on both synthetic and real LLVE datasets.

Lin Liu, Junfeng An, Jianzhuang Liu, Shanxin Yuan, Xiangyu Chen, Wengang Zhou, Houqiang Li, Yanfeng Wang, Qi Tian• 2022

Related benchmarks

TaskDatasetResultRank
Low-light Video EnhancementSDSD outdoor
PSNR24.09
18
Low-light Video EnhancementDID
PSNR23.85
18
Low-light Video EnhancementSDSD indoor
PSNR26.19
18
Low-light Video EnhancementSMID
PSNR25.31
18
Low-light Video EnhancementDAVIS
PSNR21.45
12
Low-light Video EnhancementYouTube-VOS (test)
PSNR22.54
12
Low-light Video EnhancementSDSD indoor
Short-Term Metric0.014
8
Low-light Video EnhancementSDSD outdoor
Short Sequence Error0.016
8
Low-light Video EnhancementDID
Short Term Metric0.021
8
Low-light Video EnhancementDAVIS
Metric Short Seq0.025
8
Showing 10 of 10 rows

Other info

Follow for update