Inverse problems in image reconstruction are fundamentally complicated by unknown noise properties. Classical iterative deconvolution approaches amplify noise and require careful parameter selection for an optimal trade-off between sharpness and grain. Deep learning methods allow for flexible parametrization of the noise and learning its properties directly from the data. Recently, self-supervised blind-spot neural networks were successfully adopted for image deconvolution by including a known point-spread function in the end-to-end training. However, their practical application has been limited to 2D images in the biomedical domain because it implies large kernels that are poorly optimized. We tackle this problem with Fast Fourier Transform convolutions that provide training speed-up in 3D microscopy deconvolution tasks. Further, we propose to adopt a Siamese invariance loss for deconvolution and empirically identify its optimal position in the neural network between blind-spot and full image branches. The experimental results show that our improved framework outperforms the previous state-of-the-art deconvolution methods with a known point spread function.

翻译：图像重建中的逆问题因未知噪声特性而变得极其复杂。经典迭代去卷积方法会放大噪声，且需要仔细选择参数以在清晰度与颗粒感之间实现最优权衡。深度学习方法允许对噪声进行灵活参数化，并直接从数据中学习其特性。近期，自监督盲点神经网络通过将已知点扩散函数纳入端到端训练，成功应用于图像去卷积。然而，其实际应用局限于生物医学领域的二维图像，因为该方法隐含的大卷积核难以优化。我们利用快速傅里叶变换卷积来解决这一问题，该技术可在三维显微图像去卷积任务中实现训练加速。此外，我们提出将孪生不变性损失应用于去卷积，并通过实验确定了该损失在盲点分支与完整图像分支之间的神经网络中的最佳位置。实验结果表明，我们改进后的框架在已知点扩散函数条件下优于先前最先进的去卷积方法。