Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis

arXiv:2303.12644v3 Announce Type: replace
Abstract: Image synthesis is expected to provide value for the translation of machine learning methods into clinical practice. Fundamental problems like model robustness, domain transfer, causal modelling, and operator training become approachable through synthetic data. Especially, heavily operator-dependant modalities like Ultrasound imaging require robust frameworks for image and video generation. So far, video generation has only been possible by providing input data that is as rich as the output data, e.g., image sequence plus conditioning in, …

arxiv cs.cv diffusion diffusion models feature synthesis type video video diffusion