论文标题
有效的盲点神经网络体系结构，用于图像降级
Efficient Blind-Spot Neural Network Architecture for Image Denoising
论文作者
论文摘要
图像DeNoising是计算摄影中必不可少的工具。使用深层神经网络的标准剥离技术需要成对的干净和嘈杂的图像进行训练。如果我们没有干净的样品，我们可以使用盲点神经网络体系结构，该结构仅根据相邻的像素来估计像素值。因此，这些网络允许直接对嘈杂的图像进行训练，因为它们逐步设计避免了琐碎的解决方案。如今，盲点主要使用转移的卷积或序列化实现。我们提出了一种新颖的完全卷积网络体系结构，该体系结构使用扩张来实现盲点特性。我们的网络改善了先前工作的性能，并在已建立的数据集上实现了最先进的结果。
Image denoising is an essential tool in computational photography. Standard denoising techniques, which use deep neural networks at their core, require pairs of clean and noisy images for its training. If we do not possess the clean samples, we can use blind-spot neural network architectures, which estimate the pixel value based on the neighbouring pixels only. These networks thus allow training on noisy images directly, as they by-design avoid trivial solutions. Nowadays, the blind-spot is mostly achieved using shifted convolutions or serialization. We propose a novel fully convolutional network architecture that uses dilations to achieve the blind-spot property. Our network improves the performance over the prior work and achieves state-of-the-art results on established datasets.
