Importance of conditioning in latent diffusion models for image generation and super-resolution
LDMs show strong potential for both augmentation and SR of photon-counting chest CT images. When guided by segmentation masks and class labels, these models preserve anatomical structure and reduce hallucination risks. The results support their use in clinically relevant scenarios, providing controllable and high-fidelity image synthesis.
Authors
- Thaís G. do Rêgo (ORCID: https://orcid.org/0000-0002-6608-4900)
- Bruno Barufaldi (ORCID: https://orcid.org/0000-0003-3954-3611)
- Telmo de Menezes Silva Filho
- Dayvison Gomes de Oliveira
- Franklin Anthony Ramos Coêlho
- Yuri de Almeida Malheiros Barbosa
Institutions
- Universidade Federal da Paraíba (BR)
- University of Bristol (GB)
- University of Pennsylvania (US)
Publication Details
- Journal
- Journal of Medical Imaging
- Published
- 2026-02-14
- DOI
- https://doi.org/10.1117/1.jmi.13.s1.s11203
- Primary Topic
- Advanced Image Processing Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00