Revisiting U-Net: a foundational backbone for modern generative AI

Journal article

This survey explores the evolution and application of U-Net in generative AI, highlighting its success across various modalities, including image, text, audio, video, 3D, and pose/action generation. Initially designed for biomedical segmentation, U-Net has been adapted and enhanced with architectural innovations such as normalization techniques, self and cross-attention mechanisms, and residual connections. These advancements have made U-Net a powerful backbone for modern generative models in diffusion-based frameworks, GANs, and autoregressive architectures. The survey comprehensively reviews U-Net’s modality-specific applications, from high-resolution image synthesis and text-to-image generation to speech enhancement, video generation, 3D reconstruction, and pose/action generation. Despite its widespread success, U-Net faces challenges in computational efficiency, contextual understanding, and scalability for multimodal tasks. Future directions focus on optimizing U-Net for lightweight and real-time applications, enhancing its contextual awareness, and improving its integration with emerging architectures like transformers and diffusion models.

Authors: Ignacio, MJ; Shin, S; Jin, H; Yoo, SJ; Han, D

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer
• Journal: Artificial Intelligence Review
• Volume: 59
• Issue: 2
• Article number: 45
• Publication date: 2025-11-24
• Acceptance date: 2025-11-11
• DOI: 10.1007/s10462-025-11450-0
• EISSN: 1573-7462
• ISSN: 0269-2821
• Language: English
• Keywords: Modality; GANs; U-Net; Generative AI; Diffusion models; Autoregressive models