论文标题
DAN：连续生物医学图像插值的变形感知网络
DAN: A Deformation-Aware Network for Consecutive Biomedical Image Interpolation
论文作者
论文摘要
连续的生物医学图像之间生物组织的连续性使视频插值算法成为可能，可以恢复生物医学图像中常见的大面积缺陷和泪液。但是，噪声和模糊差异，较大的变形以及生物医学图像之间的漂移使任务具有挑战性。为了解决该问题，本文引入了一个变形感知网络，以根据生物组织的连续性合成每个像素。首先，我们为连续的生物医学图像插值开发了一个变形层，该层隐含地采用了全局感知变形。其次，我们提出了一种自适应样式的平衡损失，以考虑连续的生物医学图像的样式差异，例如模糊和噪声。在变形感知模块的指导下，我们从一个全局域中合成每个像素，从而进一步改善了像素合成的性能。基准数据集上的定量和定性实验表明，所提出的方法优于最先进的方法。
The continuity of biological tissue between consecutive biomedical images makes it possible for the video interpolation algorithm, to recover large area defects and tears that are common in biomedical images. However, noise and blur differences, large deformation, and drift between biomedical images, make the task challenging. To address the problem, this paper introduces a deformation-aware network to synthesize each pixel in accordance with the continuity of biological tissue. First, we develop a deformation-aware layer for consecutive biomedical images interpolation that implicitly adopting global perceptual deformation. Second, we present an adaptive style-balance loss to take the style differences of consecutive biomedical images such as blur and noise into consideration. Guided by the deformation-aware module, we synthesize each pixel from a global domain adaptively which further improves the performance of pixel synthesis. Quantitative and qualitative experiments on the benchmark dataset show that the proposed method is superior to the state-of-the-art approaches.
