… In this chapter, we deal with depth estimation using Convolutional Neural Network (CNN) …
with the problem of “depth estimation from a single image by convolutional neural networks”. …

… single-input deep neural networks. The other novelty of this work lies in its generation of an
image … We compared the proposed MIRes CNN model with two Single-Input deep Residual …

… settings of deep learning network so far, we mainly refer to some famous network parameter
settings. In addition, according to the principle of maximizing network performance and …

… This paper portrays various image denoising models based on deep CNN as they showed
the best denoised image as output in performance and accuracy in image denoising than …

… from training images (TIs) hidden in deep learning. This paper proposes a reconstruction
method using a deep residual deconvolution network (DRDN), considered as a variant of deep …

… In this project, the depth information is extracted in the form of a depth map. A depth map is
an image … In this work, we propose a monocular depth estimation using encoder and decoder …

… For better understanding the depth changes at the image gradients, we use an inception
layer pipe to adjust the origin disparity maps generated by CNN residual network. Instead of …

… divide the joint DOA estimation into two … deep learning method is proposed to estimate
azimuths and elevations separately. In our work, azimuth estimation and elevation estimation use …

… the average error of the predicted depth map, where n is the number of pixels in depth
map, ypredict and ytrue are the predicted depth map and ground truth depth map respectively. …

… [21] used single processing techniques, ie, wavelet idea and CNN to implement a good
performance in image denoising. Inspired by that, we also use deep CNNs for image denoising …