Deep learning in motion deblurring: current status, benchmarks and future prospects

TL;DR

The paper addresses blind motion deblurring, where the blur is unknown and often nonuniform, challenging traditional kernel-based methods. It synthesizes deep learning approaches by backbone—CNN, RNN, GAN, and Transformer—and contrasts two-stage kernel-estimation pipelines with end-to-end learning, highlighting their respective strengths and limitations. It catalogs datasets (synthetic and real) and evaluation metrics, benchmarks SOTA methods on GoPro, HIDE, RealBlur, and related datasets, and finds Transformer-based methods—especially efficient variants like FFTformer and Restormer—offering the best PSNR/SSIM in many cases, albeit at higher computational cost. The study highlights practical implications for robust image restoration in real-world blur, points to challenges in model efficiency, high-level vision applicability, and data scarcity, and points to diffusion-based methods as a promising future avenue.

Abstract

Motion deblurring is one of the fundamental problems of computer vision and has received continuous attention. The variability in blur, both within and across images, imposes limitations on non-blind deblurring techniques that rely on estimating the blur kernel. As a response, blind motion deblurring has emerged, aiming to restore clear and detailed images without prior knowledge of the blur type, fueled by the advancements in deep learning methodologies. Despite strides in this field, a comprehensive synthesis of recent progress in deep learning-based blind motion deblurring is notably absent. This paper fills that gap by providing an exhaustive overview of the role of deep learning in blind motion deblurring, encompassing datasets, evaluation metrics, and methods developed over the last six years. Specifically, we first introduce the types of motion blur and the fundamental principles of deblurring. Next, we outline the shortcomings of traditional non-blind deblurring algorithms, emphasizing the advantages of employing deep learning techniques for deblurring tasks. Following this, we categorize and summarize existing blind motion deblurring methods based on different backbone networks, including convolutional neural networks, generative adversarial networks, recurrent neural networks, and Transformer networks. Subsequently, we elaborate not only on the fundamental principles of these different categories but also provide a comprehensive summary and comparison of their advantages and limitations. Qualitative and quantitative experimental results conducted on four widely used datasets further compare the performance of SOTA methods. Finally, an analysis of present challenges and future pathways. All collected models, benchmark datasets, source code links, and codes for evaluation have been made publicly available at https://github.com/VisionVerse/Blind-Motion-Deblurring-Survey

Figures (13)

• Figure 1: Sharp-blurry images.
• Figure 2: An overview of traditional and deep learning methods for blind motion deblurring.
• Figure 3: An overview of deep learning methods for blind motion deblurring.
• Figure 4: Two CNN-based blind motion deblurring frameworks.
• Figure 5: Different end-to-end CNN-based blind motion deblurring network architectures.