CVDec 21, 2022

Low-Light Image and Video Enhancement: A Comprehensive Survey and Beyond

arXiv:2212.10772v544 citationsh-index: 41Has Code
Originality Synthesis-oriented
AI Analysis

It addresses dataset limitations for researchers in low-light image and video enhancement, but is incremental as it primarily surveys and extends existing resources.

This paper tackles the lack of datasets for mixed over-/under-exposed images and low-light videos by introducing SICE_Grad, SICE_Mix, and the Night Wenzhou dataset, and conducts comparative experiments to analyze techniques in low-light enhancement.

This paper presents a comprehensive survey of low-light image and video enhancement, addressing two primary challenges in the field. The first challenge is the prevalence of mixed over-/under-exposed images, which are not adequately addressed by existing methods. In response, this work introduces two enhanced variants of the SICE dataset: SICE_Grad and SICE_Mix, designed to better represent these complexities. The second challenge is the scarcity of suitable low-light video datasets for training and testing. To address this, the paper introduces the Night Wenzhou dataset, a large-scale, high-resolution video collection that features challenging fast-moving aerial scenes and streetscapes with varied illuminations and degradation. This study also conducts an extensive analysis of key techniques and performs comparative experiments using the proposed and current benchmark datasets. The survey concludes by highlighting emerging applications, discussing unresolved challenges, and suggesting future research directions within the LLIE community. The datasets are available at https://github.com/ShenZheng2000/LLIE_Survey.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes