AI RESEARCH

Flexible Control of 3D CT Generation via Text and Semantically-Defined Segmentation Prompts

arXiv CS.CV

ArXi:2606.00967v1 Announce Type: new Generative models for volumetric medical images have found many applications in medical imaging, ranging from data augmentation to serving as priors for inverse problems. For these applications, generating high-resolution 3D images with strong controllability is essential but remains highly challenging. Existing approaches typically control generation either through radiology reports used as text prompts or through full image segmentation.