arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.10884eess.IVcs.CV
收藏

在W2S上使用深度学习进行显微图像恢复

Microscopy Image Restoration using Deep Learning on W2S

EPFL(洛桑联邦理工学院)

Martin Chatton

摘要:

我们利用深度学习技术来联合去噪和超分辨率荧光显微镜采集的生物医学图像。我们开发了一种基于最近W2S论文中描述的网络和方法的深度学习算法,以解决联合去噪和超分辨率问题。具体来说,我们解决SIM图像从宽视场图像的恢复。我们的TensorFlow模型是在W2S细胞图像数据集上训练的,可以在这个存储库中在线访问:https://github.com/mchatton/w2s-tensorflow。在测试图像上,该模型显示出视觉上令人信服的去噪效果,并将分辨率提高了两倍。对于512 $\times$ 512图像,推断在Titan X GPU上花费不到1秒,在普通CPU上花费大约15秒。我们进一步提出了在训练中使用的损失的不同变化的结果。

英文摘要:

We leverage deep learning techniques to jointly denoise and super-resolve biomedical images acquired with fluorescence microscopy. We develop a deep learning algorithm based on the networks and method described in the recent W2S paper to solve a joint denoising and super-resolution problem. Specifically, we address the restoration of SIM images from widefield images. Our TensorFlow model is trained on the W2S dataset of cell images and is made accessible online in this repository: https://github.com/mchatton/w2s-tensorflow. On test images, the model shows a visually-convincing denoising and increases the resolution by a factor of two compared to the input image. For a 512 $\times$ 512 image, the inference takes less than 1 second on a Titan X GPU and about 15 seconds on a common CPU. We further present the results of different variations of losses used in training.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑