Diffusion models have become a popular approach for image generation and reconstruction due to their numerous advantages. However, most diffusion-based inverse problem-solving methods only deal with 2D images, and even recently published 3D methods do not fully exploit the 3D distribution prior. To address this, we propose a novel approach using two perpendicular pre-trained 2D diffusion models to solve the 3D inverse problem. By modeling the 3D data distribution as a product of 2D distributions sliced in different directions, our method effectively addresses the curse of dimensionality. Our experimental results demonstrate that our method is highly effective for 3D medical image reconstruction tasks, including MRI Z-axis super-resolution, compressed sensing MRI, and sparse-view CT. Our method can generate high-quality voxel volumes suitable for medical applications.
翻译:传播模型因其众多优势而成为人们在图像生成和重建中流行的一种方法。 然而,大多数基于传播的反向解决问题的方法只涉及2D图像,甚至最近公布的3D方法也没有充分利用之前的3D分布。为了解决这个问题,我们提议了一种新颖的方法,用两种垂直的2D预先训练的2D传播模型来解决3D反向问题。通过将3D数据传播作为2D分布的产物进行建模,我们的方法有效地解决了维度的诅咒。我们的实验结果表明,我们的方法对于3D的医学图像重建任务非常有效,包括MRI Z-xis超级分辨率、压缩传感器MRI和分散式CT。我们的方法可以产生适合医疗应用的高品质的Voxel数量。</s>