diffusion models 1fréchet distance loss 1medical image synthesis 1synthetic data augmentation 1tumor segmentation 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CV2026
Improving Medical Image Generative Models with Fréchet Distance Loss
Andrew Marshall, Xuanang Xu, Xiaoran Zhang +3
The paper introduces a Fréchet Distance loss to fine‑tune diffusion generative models so they better reproduce the irregular shapes of tumors in medical images, leading to higher-q…
eess.IV2026
Subject-Specific Low-Field MRI Synthesis via a Neural Operator
Ziqi Gao, Nicha Dvornek, Xiaoran Zhang +3
Low-field (LF) magnetic resonance imaging (MRI) improves accessibility and reduces costs but generally has lower signal-to-noise ratios and degraded contrast compared to high field…
cs.CV2026
High-Quality and Efficient Turbulence Mitigation with Events
Xiaoran Zhang, Jian Ding, Yuxing Duan +4
Turbulence mitigation (TM) is highly ill-posed due to the stochastic nature of atmospheric turbulence. Most methods rely on multiple frames recorded by conventional cameras to capt…