Abstract: Given the pivotal role of China's coal industry in ensuring energy security and economic development, coupled with the national strategic goals of achieving carbon peak and carbon neutrality as well as advancing energy revolution, the construction of intelligent mines has gradually emerged as a core pathway for the transformation and upgrading of the coal industry. Intelligent mining aims to promote high-quality development of the coal sector through technological innovation, emphasizing not only the improvement of production efficiency and safety but also the precise acquisition and processing of data in complex environments. However, the complex and variable conditions in mine environments, including insufficient lighting, dust, and equipment noise, often result in the acquisition of low-quality images, which significantly hinder the effectiveness of vision-based intelligent monitoring and analysis systems. The inability of low-quality images to meet the requirements of high-precision recognition and analysis in critical areas such as mine safety production, equipment condition monitoring, and disaster early warning has become a major technical bottleneck in the advancement of intelligent mining. In this context, image super-resolution reconstruction technology, as a key technique capable of restoring high-resolution details from low-resolution images, has garnered widespread attention from both academia and industry in recent years. Furthermore, it is gradually becoming an effective solution to address image quality issues in complex mine environments. By leveraging image processing and deep learning methods, super-resolution reconstruction technology can significantly enhance the clarity and detail representation of low-quality images, thereby providing high-quality visual data support for intelligent mining. Due to the unique demands and broader requirements of mine environments for image super-resolution technology, research on key technologies for super-resolution reconstruction of low-quality images in complex mine environments holds significant theoretical and practical value. The current status of image super-resolution reconstruction technology and its application progress in complex mine environments are systematically elaborated. Firstly, the technology is categorized and overviewed from a methodological perspective, with detailed explanations of the fundamental principles and mathematical foundations of three main approaches: interpolation-based, reconstruction-based, and learning-based methods. Secondly, from the perspective of technological evolution, the development process from traditional methods to deep learning methods is reviewed, with a focus on analyzing the technical characteristics and implementation mechanisms of mainstream deep learning methods such as convolutional neural networks, generative adversarial networks, and Transformers. A comparative analysis of the performance metrics, applicable scenarios, and limitations of various methods is also provided. Concurrently, experimental analyses were performed to evaluate the performance of these leading deep learning-based super-resolution models specifically within the complex environment of mines. Building on this, the unique challenges of image super-resolution reconstruction under complex conditions such as low illumination, high noise, and non-uniform degradation in mine environments are thoroughly explored. Targeted solutions are proposed from dimensions including physical degradation model construction, multi-modal data fusion, and lightweight network design. Finally, based on the current research progress and practical application needs, future development directions for image super-resolution reconstruction technology in mine environments are outlined. Through the systematic organization of theoretical methods, the summarization of technological advancements, and the analysis of challenges and countermeasures, methodological references for theoretical innovation in image super-resolution reconstruction in complex mine environments are provided, and practical guidance for the engineering application of related technologies is offered to promote the construction of intelligent mines and the improvement of safety production levels.