图像去模糊是计算机视觉的基础任务，对医学影像、监控摄像及卫星图像等方面具有重要意义。对于真实场景去模糊任务，由于场景内可能存在多个目标以及复杂的运动，成像过程容易受到许多外界因素的干扰，例如噪声、光照等，使图像去模糊问题更复杂。起初的研究主要针对仿真降质，但由于仿真模型受到多种假设限制，例如高斯噪声和全局一致运动等，难以在真实场景下展现出良好的复原效果。因此，越来越多的学者着手研究真实场景去模糊问题，以提升去模糊方法在现实生活中的使用价值。由于当前对真实场景下去模糊问题的综述性研究还处于空白阶段，为此本文对真实场景去模糊任务进行了系统调研，分析其中存在的挑战，从降质模型的角度出发，由浅入深，由易到难，将真实场景下的去模糊问题拆解开，归纳为单一模糊去除方法、复合模糊去除方法、以及真实场景下未知模糊的去除方法，全方位描述了当前学术界在该问题上的研究内容和方法，总结和对比了各类方法的优缺点，阐述了阻碍复原性能进一步提升的难点问题，并对常用的一些数据集和评价指标做了整理总结。最后，真实场景去模糊任务的未来发展前景和研究热点进行了展望，并给出了可能的解决方法。

Objective Image deblurring is a fundamental task in the field of computer vision, holding significant importance in various applications such as medical imaging, surveillance cameras, and satellite imagery. Over the years, it has garnered substantial attention from researchers, leading to the development of numerous dedicated methods. However, in real-world scenarios, the imaging process may be subject to various disturbances, presenting a more complex blur. Factors such as inconsistent object motion, camera lens defocusing, pixel compression during transmission, and insufficient lighting can lead to a range of intricate blurring phenomena, and the deblurring challenges are further amplified. Consequently, image deblurring in real-world scenarios is a complex ill-posed problem. In these circumstances, conventional image deblurring based on simulated blurry degradations methods often falls short when confronted with the intricacies of real-world deblurring challenges. The primary reason for these limitations is the extent of assumptions that conventional methods rely on. These assumptions include but are not limited to 1) traditional methods often assume that the noise in the image follows a Gaussian distribution, 2) Spatially invariant uniform blur assumption, and 3) Independence of blurring phenomena assumption. While convenient for theoretical analysis and algorithm development, these assumptions prove to be restrictive when applied to the complex deblurring problems encountered in real-world scenarios. Consequently, there is a pressing need to conduct specialized research tailored to the challenges of real-world image deblurring and to enhance the effectiveness of image restoration methods. Real-world image deblurring is an intricate task that requires the development of innovative algorithms and techniques capable of accommodating the diversity of blurring factors and complexities present in practical environments. The researchers embarked on this journey to create unique deblurring solutions that better handle real-world scenarios and the practical applicability of deblurring methods. Method One approach to addressing these challenges is to design algorithms that are robust to various types of noise and are capable of handling non-uniform and coupled blurring effects. Additionally, machine learning and deep learning have emerged as powerful tools for addressing complex real-world deblurring problems. Deep learning models, such as convolution neural networks (CNNs) and generative adversarial networks (GANs) have shown remarkable adaptability in learning from diverse data and producing high-quality deblurred images. Furthermore, researchers are exploring the integration of multiple sensor inputs, including depth information, to improve deblurring accuracy and effectiveness. These multi-modal approaches leverage additional data sources to disentangle complex blurring effects and enhance deblurring performance. As real-world image deblurring continues to gain attention, the research community is expected to contribute valuable insights and develop innovative solutions to further improve image restoration in complex scenarios. The ongoing collaboration between researchers from different fields, including computer vision, machine learning, optics, and imaging, will likely yield breakthroughs in addressing real-world deblurring challenges. In conclusion, real-world image deblurring is a multifaceted problem that requires tailored solutions to overcome the limitations of conventional deblurring methods. By acknowledging the complexities of real-world blurring phenomena and harnessing the power of advanced algorithms, machine learning, and multi-modal approaches, researchers are working towards enhancing image restoration in practical, challenging environments. Result and Conclusion Despite the growing interest in real-world deblurring, there remains a dearth of comprehensive surveys on the subject. To bridge this gap, this paper conducts a systematic review of real-world deblurring problems. From the perspective of image degradation models, it delves into various aspects, breaking down the challenges into isolated blur removal methods, coupled blur removal methods, and methods for unknown blur in real-world scenarios. The paper provides a holistic overview of the state-of-the-art research in this domain, summarizing and contrasting the strengths and weaknesses of various methods, and elucidates the challenges hindering further improvements in restoration performance. Finally, the paper offers insights into the prospects and research trends in real-world deblurring tasks, presenting potential solutions to address the challenges ahead. These challenges and solutions include: 1) Shortage of paired real-world training data: Acquiring high-quality training data with blur and sharp images that accurately represent the diversity of real-world scenarios is a significant challenge. The scarcity of comprehensive, real-world datasets hinders the development of supervised deblurring tasks. To address the lack of real-world data, researchers are exploring data synthesis and unsupervised learning techniques. By generating synthetic data that simulate real-world scenarios, algorithms can be trained on more diverse data, while unsupervised learning is more suitable for improving adaptability to real-world conditions. 2) Efficiency of complex models: Recent deblurring algorithms rely on complex deep learning models to achieve high-quality results. However, the models often result in computational inefficiency, making these algorithms impractical for real-time or resource-constrained applications. The computational overhead and memory requirements of these models limit their deployment in practical scenarios. Researchers are developing more efficient model architectures, such as lightweight neural networks and model compression techniques. These models aim to strike a balance between computational efficiency and deblurring performance, making them suitable for real-time applications and resource-constrained environments. 3) Overemphasis on degradation metrics: Many deblurring methods prioritize optimizing quantitative metrics related to the reconstruction of image details. While these metrics provide a quantitative measure of image quality, they may not align with the perceptual quality as perceived by the human visual system. Therefore, a narrow focus on these metrics may neglect the importance of achieving results that are visually realistic and aesthetically pleasing to human observers. Recently, there has been a growing emphasis on perceptual quality metrics. These metrics evaluate the visual quality of deblurred images based on human perception. Integrating perceptual quality metrics into the evaluation process can help ensure that deblurred images are not only quantitatively accurate but also visually pleasing to humans. As the real-world image deblurring research continues, it is expected that these challenges will be gradually addressed, leading to more effective and practical deblurring solutions. This survey aims to provide a comprehensive understanding of the current landscape of research in real-world deblurring and offers a roadmap for further advancements in this critical area of computer vision.