Deep Learning Enhanced Computational Imaging: Leveraging AI for Advanced Image Reconstruction and Analysis

Computational imaging is a multidisciplinary field that combines optics, signal processing, and mathematical algorithms to enhance the capabilities of imaging systems. Traditional imaging techniques often face limitations in terms of resolution, signal-to-noise ratio, and speed. Computational imaging approaches address these challenges by leveraging advanced algorithms to reconstruct high-quality images from incomplete or indirect measurements. The emergence of deep learning (DL) has revolutionized computational imaging, exhibiting remarkable performance in tasks such as image reconstruction, classification, object detection and segmentation, and super-resolution. By leveraging the power of deep learning, computational imaging systems have witnessed significant improvements in terms of image quality, processing speed, and overall versatility. The integration of deep learning into computational imaging has opened up exciting possibilities across various applications. However, there remain gaps in understanding the full potential and limitations of these techniques, as well as ongoing debates about the best practices for integrating DL models with traditional computational imaging methods.

This Research Topic aims to highlight the most recent advancements, applications, and challenges in deep learning-enhanced computational imaging. It aims to provide a comprehensive overview of the state-of-the-art techniques, methodologies, and applications that harness the power of deep learning to enhance computational imaging performance. This includes the deep learning model for image preprocessing, reconstruction and analysis, the newly developed deep learning model, and the applications of deep learning-based techniques. Specific questions to be addressed include how DL can be optimized for various imaging tasks, what new DL architectures can be developed for better performance, and how physical knowledge can be integrated into DL models to improve interpretability and reliability.

To gather further insights in the integration of deep learning with computational imaging, we welcome articles addressing, but not limited to, the following themes:
• DL-based methods for addressing ill-posed inverse problems.
• Application of DL techniques in various aspects of image analysis, such as denoising, super-resolution, image classification, segmentation, and registration.
• Reinforcement learning to optimize imaging acquisition protocols.
• Novel approaches that integrate physical knowledge into neural network models, enhancing the interpretability and performance of DL-based methods.
• Advancements in DL architectures for improved computational imaging outcomes, such as transfer learning, continual learning, and self-supervised learning.
• Performance analysis of DL-based methods, including assessments of uncertainty and generalization capabilities.

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Conceptual Analysis
• Data Report
• Editorial
• FAIR² Data
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• ... View all formats

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Conceptual Analysis
• Data Report
• Editorial
• FAIR² Data
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Review

Keywords: Deep learning, optical imaging, artificial intelligence, computational imaging

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.