Convolutional neural networks have achieved tremendous success in the areas of image processing and computer vision. However, they experience problems with low-frequency information such as semantic and category content and background color, and high-frequency information such as edge and structure. We propose an efficient and accurate deep learning framework called the multi-frequency feature extraction and fusion network (MFFNet) to perform image processing tasks such as deblurring. MFFNet is aided by edge and attention modules to restore high-frequency information and overcomes the multiscale parameter problem and the low-efficiency issue of recurrent architectures. It handles information from multiple paths and extracts features such as edges, colors, positions, and differences. Then, edge detectors and attention modules are aggregated into units to refine and learn knowledge, and efficient multi-learning features are fused into a final perception result. Experimental results indicate that the proposed framework achieves state-of-the-art deblurring performance on benchmark datasets.
We consider pointwise asymptotic confidence intervals for images that are blurred and observed in additive white noise. This amounts to solving a stochastic inverse problem with a convolution operator. Under suitably modified assumptions, we fill some apparent gaps in the proofs published in [N. Bissantz, M. Birke, Asymptotic normality and confidence intervals for inverse regression models with convolution-type operators, J. Multivariate Anal. 100 (2009), 2364-2375]. In particular, this leads to modified bootstrap confidence intervals with much better finite-sample behaviour than the original ones, the validity of which is, in our opinion, questionable. Some simulation results that support our claims and illustrate the behaviour of the confidence intervals are also presented.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.