Bridging Signal Processing and Generative AI: Advances in Image Modeling, Flow Matching, Diffusion Models and Deep Generative Architectures

Dear Colleagues,

Generative Artificial Intelligence (GenAI) has profoundly transformed the landscape of image and signal processing, enabling unprecedented synthesis, reconstruction, and enhancement capabilities. From denoising and super-resolution to cross-modal generation and inverse problems, GenAI frameworks have redefined how data is represented, processed, and understood.

This Special Issue aims to bring together cutting-edge research at the intersection of signal processing and generative modeling. We invite contributions exploring theoretical advances, computational models, and real-world applications that exploit the synergy between traditional signal processing principles and modern generative paradigms — including Diffusion Models, Flow Matching, GANs, VAEs, and hybrid architectures.

Flow Matching, in particular, has recently emerged as a promising successor to diffusionbased models, offering a unified framework for training deterministic generative flows via continuoustime transport equations. This paradigm bridges score-based and flow-based learning, providing more stable dynamics, efficient training, and seamless multimodal generalization.

By fostering discussion across these domains, this Special Issue seeks to consolidate the scientific foundation of Generative AI and stimulate advances that are both mathematically rigorous and practically impactful.

Topics of Interest (include but are not limited to)

• Generative Modeling for Images and Signals: Diffusion, Flow Matching, GANs, VAEs, Normalizing Flows, and hybrid architectures.
• Flow-based generative processes and transport formulations for image and signal synthesis.
• Signal Processing in Generative Pipelines: denoising, restoration, compression, superresolution, enhancement, and inverse problems.
• Cross-modal and Multimodal Systems integrating visual, auditory, textual, and sensory data.
• Physics- and Data-driven Signal Priors for stable and explainable generative reconstruction.
• Real-time and Embedded Generative Processing for edge devices and low-power platforms.
• Evaluation Metrics, Robustness, and Interpretability in Flow- and Diffusion-based generative models.
• Responsible and Ethical Use of generative signal and image technologies.
• Applications: medical imaging, remote sensing, robotics, autonomous systems, creative media, and smart infrastructure.

Dr. Clodoaldo Aparecido De Moraes Lima
Guest Editor

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-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.