Image Processing and Computer Vision

Dear Colleagues,

Image processing and computer vision constitute core areas in artificial intelligence, underpinning a wide spectrum of applications ranging from robotics and autonomous driving to medical imaging and human–computer interaction. With the rapid progress in deep learning, especially the emergence of large multimodal foundation models and the integration of language and vision, the field is experiencing a significant paradigm shift—from isolated, task-specific pipelines to more unified, general-purpose representations.

This Special Issue aims to highlight recent advances and emerging challenges in image processing and computer vision, with a particular emphasis on different levels and modalities. At the low level, research continues to improve robustness, efficiency, and quality in classic tasks such as denoising, deblurring, super-resolution, and compression. Meanwhile, high-level tasks—such as segmentation, detection, captioning, and visual reasoning—are increasingly being tackled with powerful backbone models that leverage 3D spatial understanding, semantic grounding, and cross-modal alignment. The arrival of vision language models (VLMs) and multimodal large language models (MLLMs) has opened new opportunities for integrating perception and cognition. At the same time, challenges remain in learning effective and transferable representations from noisy, incomplete, or weakly labeled data, especially in 3D scenes and real-world long-tailed scenarios. Accordingly, this Special Issue aims to gather cutting-edge research that advances the state of the art in image processing and computer vision across all levels of visual understanding.

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

• Low-level vision: denoising, deblurring, super-resolution, and enhancement;
• High-level vision: detection, segmentation, tracking, and scene understanding;
• Representation learning for 2D/3D visual data;
• Vision-language models and multimodal large language models;
• 3D scene reconstruction and understanding;
• Cross-modal alignment and fusion;
• Learning with limited, noisy, or long-tailed data;
• Efficient deep learning and lightweight architectures;
• Applications in medical imaging, autonomous driving, and remote sensing.

Dr. Shuting He
Prof. Dr. Henghui Ding
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 100 words) can be sent to the Editorial Office for announcement on this website.

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-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly 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 2600 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.

• computer vision
• image processing
• low-level vision
• high-level vision
• representation learning
• multimodal large language models (MLLMs)
• 3D vision
• lightweight deep learning