Advanced Image Processing and Computer Vision (3rd Edition)

Dear Colleagues,

Advanced Image Processing (AIP) and Computer Vision (CV) are broad research areas that continue to drive innovation and exert a significant impact across a wide range of real-world applications.

Today, Artificial Intelligence (AI) permeates many aspects of daily life. Among AI-based methodologies, convolutional neural networks and vision transformers represent the core technologies for AIP and CV, often integrated with large language models in multimodal settings. Beyond these paradigms, a wide range of complementary models and learning strategies have been increasingly explored in the literature, including graph neural networks, generative models (e.g., variational autoencoders and diffusion models), self-supervised and contrastive learning frameworks, foundation models, and physics-informed or hybrid data-driven approaches. In addition, classical signal processing and optimization-based techniques are frequently combined with deep learning architectures to improve robustness and interpretability. Although these approaches have achieved remarkable success, current technologies still primarily demonstrate strong performance from a data-driven perspective. Consequently, there is an urgent need for novel AI-based algorithms for AIP and CV, particularly in research fields where data scarcity, limited data quality, domain shift, and challenges around data interpretation and understanding remain critical issues. Moreover, increasing attention must be devoted to uncertainty modeling, explainability, robustness, and trustworthiness. In this context, the importance of a human-centric AI paradigm should be emphasized, ensuring that developed technologies are ethical, transparent, explainable, and fair.

Following the success of the previous edition of this Special Issue, “Advanced Image Processing and Computer Vision (2nd Edition)”, this third Edition aims to gather original research articles, comprehensive literature reviews, and in-depth technical reports addressing the design, development, and/or deployment of AI-based algorithms for AIP and CV in real-world application scenarios, such as medicine.

Topics of interest include, but are not limited to, the following:

• Convolutional neural networks and vision transformers for AIP and CV;
• Multimodal learning and integration with large language models;
• Graph neural networks for visual data analysis;
• Generative models (e.g., VAEs, GANs, diffusion models);
• Self-supervised and contrastive learning;
• Foundation models for vision tasks;
• Physics-informed and hybrid data-driven approaches;
• Classical signal processing combined with deep-learning techniques;
• Uncertainty modeling and probabilistic learning in vision systems;
• Explainable and interpretable AI for image processing and computer vision;
• Robust and trustworthy AI in visual applications;
• Domain adaptation and learning under data scarcity;
• Neuromorphic approaches for image processing and vision;
• TinyML and resource-efficient AI for edge vision applications;
• Real-world applications, especially in medical imaging and healthcare;
• DataOps and MLOps.

Dr. Selene Tomassini
Dr. M. Ali Akber Dewan
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the Special Issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Computers is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.