Dear Colleagues,

In recent years, rapid advances in deep learning, convolutional neural networks, transformer architectures, and large foundation models have dramatically reshaped the fields of image processing and computer vision. Novel computational frameworks enable breakthroughs in image enhancement, restoration, segmentation, object detection, feature extraction, pattern recognition, and multimodal understanding. Meanwhile, real-world applications—including medical imaging, intelligent surveillance, autonomous systems, remote sensing, industrial inspection, and human–computer interaction—demand more robust, efficient, and interpretable vision-based algorithms. Despite substantial progress, many challenges remain, including domain adaptation, low-data learning, model generalization, real-time performance, and the integration of vision with sensory and contextual data.

This Special Issue, entitled Recent Progress in Image Processing and Computer Vision, aims to collect high-quality original research articles, review papers, and technical communications that address fundamental theories, innovative methodologies, and practical implementations in image processing and computer vision. We welcome contributions across algorithm design, network architecture optimization, multimodal fusion, weakly supervised and self-supervised learning, transfer learning, explainable AI for vision, and real-world deployment of vision systems. The scope covers both methodological advances and application-driven studies that extend the boundaries of traditional image processing and modern data-driven computer vision.

By gathering cutting-edge work from academia and industry, this collection will complement existing literature by highlighting recent developments—especially those involving deep learning and large-scale models—and bridging theoretical advances with realistic application scenarios. It will serve as a valuable reference for researchers, engineers, and students pursuing state-of-the-art image and vision technologies, while stimulating further innovation in this fast-evolving field.

Dr. Shuwen Chen
Prof. Dr. Yudong Zhang