Abstract
Deep learning-based low-light image enhancers have made significant progress in recent years, with a trend towards achieving satisfactory visual quality while gradually reducing the number of parameters and improving computational efficiency. In this work, we aim to delving into the limits of image enhancers both from visual quality and computational efficiency, while striving for both better performance and faster processing. To be concrete, by rethinking the task demands, we build an explicit connection, i.e., visual quality and computational efficiency are corresponding to model learning and structure design, respectively. Around this connection, we enlarge parameter space by introducing the re-parameterization for ample model learning of a pre-defined minimalist network (e.g., just one layer), to avoid falling into a local solution. To strengthen the structural representation, we define a hierarchical search scheme for discovering a task-oriented re-parameterized structure, which also provides powerful support for efficiency. Ultimately, this achieves efficient low-light image enhancement using only a single convolutional layer, while maintaining excellent visual quality. Experimental results show our sensible superiority both in quality and efficiency against recently-proposed methods. Especially, our running time on various platforms (e.g., CPU, GPU, NPU, DSP) consistently moves beyond the existing fastest scheme. The source code will be released at this https URL.
Abstract (translated)
基于深度学习的低光图像增强技术近年来取得了显著进展，尤其是在实现令人满意的视觉质量的同时逐渐减少参数数量并提高计算效率方面。在本项工作中，我们旨在深入探究图像增强器在视觉质量和计算效率方面的极限，并努力同时提升性能和加快处理速度。具体而言，通过重新思考任务需求，我们建立了明确的联系：即视觉质量和计算效率分别对应于模型学习和结构设计。围绕这一联系，我们通过引入重参数化来扩大预定义极简网络（例如仅一层）的学习空间，以避免陷入局部最优解，并为充分利用该预定义网络提供条件。为了加强结构表示能力，我们定义了分层搜索方案，用于发现面向任务的重新参数化结构，这同时也为效率提供了强大支持。最终，在保持出色视觉质量的前提下，使用单一卷积层实现了高效的低光图像增强。 实验结果表明，在质量和效率方面，我们的方法相对于最近提出的其他方法具有明显的优越性。特别是在各种平台（如CPU、GPU、NPU和DSP）上的运行时间上，我们超越了现有的最快方案。源代码将在此网址发布：[此链接为示例占位符，请替换为实际的URL]。 请注意，在提供具体链接时，确保使用有效的URL，并且根据实际情况填写正确的网站或GitHub仓库地址。
URL
https://arxiv.org/abs/2502.19867
