Visually-Guided Controllable Medical Image Generation via Fine-Grained Semantic Disentanglement
通过细粒度语义解耦实现视觉引导的可控医学图像生成
机构 * Computer Science and Engineering, Northeastern University, Shenyang, China(东北大学计算机科学与工程系,中国沈阳) ; Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education, Northeastern University, Shenyang, China(教育部医学图像智能计算重点实验室,东北大学,中国沈阳) ; National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Shenyang, China(工业智能与系统优化国家级前沿科学中心,中国沈阳) ; AiShiWeiLai AI Research, China(艾世维来人工智能研究,中国) ; Amii, University of Alberta, Edmonton, Alberta, Canada(阿尔伯塔大学艾米人工智能研究所,加拿大埃德蒙顿,阿尔伯塔)
AI总结 本文提出视觉引导的文本解耦框架,通过细粒度语义解耦提升医学图像生成的可控性和生成质量。
Comments 10 pages, 7 figures. Currently under review