Tatana Mpilo M, Tsoeu Mohohlo S, Maswanganyi Rito C
Department of Electronic and Computer Engineering, Durban University of Technology, Durban 4001, South Africa.
Steve Biko Campus, Durban University of Technology, Durban 4001, South Africa.
J Imaging. 2025 Apr 21;11(4):125. doi: 10.3390/jimaging11040125.
Computer vision aims to enable machines to understand the visual world. Computer vision encompasses numerous tasks, namely action recognition, object detection and image classification. Much research has been focused on solving these tasks, but one that remains relatively uncharted is light enhancement (LE). Low-light enhancement (LLE) is crucial as computer vision tasks fail in the absence of sufficient lighting, having to rely on the addition of peripherals such as sensors. This review paper will shed light on this (focusing on video enhancement) subfield of computer vision, along with the other forementioned computer vision tasks. The review analyzes both traditional and deep learning-based enhancers and provides a comparative analysis on recent models in the field. The review also analyzes how popular computer vision tasks are improved and made more robust when coupled with light enhancement algorithms. Results show that deep learners outperform traditional enhancers, with supervised learners obtaining the best results followed by zero-shot learners, while computer vision tasks are improved with light enhancement coupling. The review concludes by highlighting major findings such as that although supervised learners obtain the best results, due to a lack of real-world data and robustness to new data, a shift to zero-shot learners is required.
计算机视觉旨在使机器能够理解视觉世界。计算机视觉涵盖众多任务，即动作识别、目标检测和图像分类。许多研究都集中在解决这些任务上，但一个相对尚未得到充分探索的领域是光照增强（LE）。低光照增强（LLE）至关重要，因为在缺乏足够光照的情况下，计算机视觉任务会失败，不得不依赖添加诸如传感器等外围设备。这篇综述论文将阐明计算机视觉的这个（专注于视频增强）子领域，以及上述其他计算机视觉任务。该综述分析了传统的和基于深度学习的增强器，并对该领域的近期模型进行了比较分析。该综述还分析了在与光照增强算法相结合时，热门的计算机视觉任务是如何得到改进并变得更稳健的。结果表明，深度学习器优于传统增强器，有监督学习器取得了最佳结果，其次是零样本学习器，而计算机视觉任务通过光照增强耦合得到了改进。该综述最后强调了主要发现，例如尽管有监督学习器取得了最佳结果，但由于缺乏真实世界数据以及对新数据的稳健性不足，需要转向零样本学习器。
