Guided depth map super-resolution: A survey
Guided depth map super-resolution (GDSR), which aims to reconstruct a high-resolution
depth map from a low-resolution observation with the help of a paired high-resolution color …
depth map from a low-resolution observation with the help of a paired high-resolution color …
Handling incomplete heterogeneous data using vaes
Variational autoencoders (VAEs), as well as other generative models, have been shown to
be efficient and accurate for capturing the latent structure of vast amounts of complex high …
be efficient and accurate for capturing the latent structure of vast amounts of complex high …
Coarse-to-fine CNN for image super-resolution
Deep convolutional neural networks (CNNs) have been popularly adopted in image super-
resolution (SR). However, deep CNNs for SR often suffer from the instability of training …
resolution (SR). However, deep CNNs for SR often suffer from the instability of training …
D-SRGAN: DEM super-resolution with generative adversarial networks
Digital elevation model (DEM) is a critical data source for variety of applications such as
road extraction, hydrological modeling, flood mapping, and many geospatial studies. The …
road extraction, hydrological modeling, flood mapping, and many geospatial studies. The …
Spatial interpolation using conditional generative adversarial neural networks
Spatial interpolation is a traditional geostatistical operation that aims at predicting the
attribute values of unobserved locations given a sample of data defined on point supports …
attribute values of unobserved locations given a sample of data defined on point supports …
Multi-attention augmented network for single image super-resolution
R Chen, H Zhang, J Liu - Pattern Recognition, 2022 - Elsevier
How to improve the representational power of visual features extracted by deep
convolutional neural networks is of crucial importance for high-quality image super …
convolutional neural networks is of crucial importance for high-quality image super …
Deep-learning-based small surface defect detection via an exaggerated local variation-based generative adversarial network
J Lian, W Jia, M Zareapoor, Y Zheng… - IEEE Transactions …, 2019 - ieeexplore.ieee.org
Surface detection of small defects plays a vital role in manufacturing and has attracted broad
interest. It remains challenging primarily due to the small size of the defect relative to the …
interest. It remains challenging primarily due to the small size of the defect relative to the …
Image super-resolution via channel attention and spatial graph convolutional network
Y Yang, Y Qi - Pattern Recognition, 2021 - Elsevier
Recently, deep convolutional neural networks (CNNs) have been widely explored in single
image super-resolution (SISR) and obtained remarkable performance. However, most of the …
image super-resolution (SISR) and obtained remarkable performance. However, most of the …
CmSalGAN: RGB-D salient object detection with cross-view generative adversarial networks
B Jiang, Z Zhou, X Wang, J Tang… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Image salient object detection (SOD) is an active research topic in computer vision and
multimedia area. Fusing complementary information of RGB and depth has been …
multimedia area. Fusing complementary information of RGB and depth has been …
Bridgenet: A joint learning network of depth map super-resolution and monocular depth estimation
Depth map super-resolution is a task with high practical application requirements in the
industry. Existing color-guided depth map super-resolution methods usually necessitate an …
industry. Existing color-guided depth map super-resolution methods usually necessitate an …