Horticulture and agriculture are considered as the important pillars of any economy. Current
technological advancements have led to the development of several new technologies …

Coarse-to-fine schemes are widely used in traditional single-image motion deblur; however
in the context of deep learning existing multi-scale algorithms not only require the use of …

As neural networks become able to generate realistic artificial images, they have the
potential to improve movies, music, video games and make the internet an even more …

Pooling has been the core ingredient of modern convolutional neural networks (CNNs).
Although classic pooling methods are simple and effective, it will inevitably lead to the …

The fast wavelet transform is an essential workhorse in signal processing. Wavelets are
local in the spatial-or temporal-and the frequency-domain. This property enables frequency …

Most of the established neural network architectures in computer vision are essentially
composed of the same building blocks (eg, convolutional, normalization, regularization …

Existing wavelet pooling methods discard the high-frequency sub-bands, which can improve
the noise-robustness of convolutional neural networks (CNNs) but lose the essential …

As neural networks become able to generate realistic artificial images, they have the
potential to improve movies, music, video games and make the internet an even more …

Applications such as medical diagnosis, navigation, robotics, etc., require 3D images.
Recently, deep learning networks have been extensively applied to estimate depth. Depth …

Spatial frequency analysis and transforms serve a central role in most engineered image
and video lossy codecs, but are rarely employed in neural network (NN)-based approaches …