论文标题
BP浸：基于反向反射的深层图像先验
BP-DIP: A Backprojection based Deep Image Prior
论文作者
论文摘要
深度神经网络是许多计算机视觉任务的非常强大的工具，包括图像修复，展示最先进的结果。但是，一旦训练中使用的观察模型在测试时间内使用的观察模型不匹配，深度学习方法的性能就会下降。此外，大多数深度学习方法都需要大量的培训数据，这些数据在许多应用中无法访问。为了减轻这些缺点，我们建议将两种图像恢复方法结合在一起：（i）深度图像先验（DIP），该方法使用给定的降级图像在测试时间内从头开始训练卷积神经网络（CNN）。它不需要任何培训数据，而是基于CNN体系结构所施加的隐式事务。 （ii）反射（BP）保真度项，这是通常在以前的浸入作品中使用的标准最小二乘损失的替代方案。我们证明了所提出的方法的性能，称为BP-DIP，在DEBLURING任务上，并显示了其优势在普通倾角上具有较高的PSNR值和更好的推理运行时。
Deep neural networks are a very powerful tool for many computer vision tasks, including image restoration, exhibiting state-of-the-art results. However, the performance of deep learning methods tends to drop once the observation model used in training mismatches the one in test time. In addition, most deep learning methods require vast amounts of training data, which are not accessible in many applications. To mitigate these disadvantages, we propose to combine two image restoration approaches: (i) Deep Image Prior (DIP), which trains a convolutional neural network (CNN) from scratch in test time using the given degraded image. It does not require any training data and builds on the implicit prior imposed by the CNN architecture; and (ii) a backprojection (BP) fidelity term, which is an alternative to the standard least squares loss that is usually used in previous DIP works. We demonstrate the performance of the proposed method, termed BP-DIP, on the deblurring task and show its advantages over the plain DIP, with both higher PSNR values and better inference run-time.
