Integrating 2D/3D Computer Vision and Signal Processing: Emerging Techniques and Future Challenges

Dear Colleagues,

Computer vision and signal processing have long been fundamental pillars of artificial intelligence, enabling machines to perceive, interpret, and respond to complex real-world environments. With the rapid evolution of deep learning, multimodal sensing, and 3D reconstruction, the integration of 2D and 3D visual understanding with advanced signal processing has become increasingly critical. While 2D image analysis underpins key tasks such as object detection, recognition, and semantic segmentation, 3D vision offers geometric and spatial context that is essential for robotics, autonomous systems, augmented and virtual reality (AR/VR), digital twins, and smart manufacturing. The convergence of computer vision and signal processing thus represents a transformative direction toward holistic and human-like visual intelligence.

Recent advances, including transformer architectures, self-supervised learning, neural radiance fields (NeRFs), and diffusion-based generative models, have significantly enhanced both visual perception and signal interpretation. At the same time, innovations in sensing hardware, such as stereo cameras, LiDAR, radar, and structured-light systems, have enabled more precise and multimodal scene understanding. Despite this progress, major challenges remain: achieving real-time inference, cross-domain generalization, robustness to noise, occlusions, and illumination variations, as well as efficient model deployment on edge and embedded platforms. Addressing these challenges calls for tighter integration between 2D/3D vision and signal processing frameworks, bridging spatial, temporal, and spectral representations to enable unified learning across modalities.

This Special Issue, “Integrating 2D/3D Computer Vision and Signal Processing: Emerging Techniques and Future Challenges,” aims to provide a multidisciplinary forum for researchers and practitioners to share innovative approaches and insights at the intersection of visual and signal-based perception. We invite original contributions that explore theoretical advances, novel architectures, and practical applications combining 2D/3D vision with signal processing across diverse domains such as robotics, autonomous driving, medical imaging, smart cities, industrial inspection, and immersive environments.

 Topics of Interest

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

• Object detection, recognition, and semantic segmentation
• Machine learning and deep learning for image, video, and signal analysis
• Visual tracking, activity recognition, and surveillance
• Face, gesture, and motion recognition
• Depth estimation, stereo vision, and multi-view geometry
• 3D reconstruction and point cloud processing
• Neural rendering and implicit scene representation
• Multimodal fusion of vision, LiDAR, radar, audio, and inertial data
• Transformer and diffusion models for spatial–temporal AI
• Lightweight and efficient networks for real-time and edge deployment
• Domain adaptation, generalization, and cross-modality learning
• Signal-driven enhancement for visual perception and reconstruction
• Applications in autonomous systems, robotics, healthcare, and AR/VR

This Special Issue will highlight the synergy between computer vision and signal processing, emphasizing unified approaches that combine geometric, photometric, and temporal cues for more reliable and interpretable visual intelligence. By gathering cutting-edge research at this intersection, the issue aims to foster collaboration, identify emerging trends, and inspire the development of next-generation intelligent systems capable of robust operation in complex and dynamic environments.

Dr. Wei Quan
Prof. Dr. Wei Li
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. Electronics 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 2400 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.

• 2D/3D computer vision
• signal processing
• deep learning
• multimodal fusion
• object detection
• visual tracking
• gesture recognition
• stereo vision
• depth estimation
• 3D reconstruction
• neural rendering
• spatial–temporal AI
• cross-domain generalization
• real-time perception
• intelligent systems