Light field spatial super-resolution using deep efficient spatial-angular separable convolution
Light field (LF) photography is an emerging paradigm for capturing more immersive
representations of the real world. However, arising from the inherent tradeoff between the …
representations of the real world. However, arising from the inherent tradeoff between the …
Three-dimensional localization microscopy using deep learning
Single molecule localization microscopy (SMLM) is one of the fastest evolving and most
broadly used super-resolving imaging techniques in the biosciences. While image …
broadly used super-resolving imaging techniques in the biosciences. While image …
Deep autoencoder for combined human pose estimation and body model upscaling
We present a method for simultaneously estimating 3D human pose and body shape from a
sparse set of wide-baseline camera views. We train a symmetric convolutional autoencoder …
sparse set of wide-baseline camera views. We train a symmetric convolutional autoencoder …
Adversarial-learning-based image-to-image transformation: A survey
Recently, the generative adversarial network (GAN) has attracted wide attention for various
computer vision tasks. GAN provides a novel concept for image-to-image transformation by …
computer vision tasks. GAN provides a novel concept for image-to-image transformation by …
Single image super-resolution using a polymorphic parallel CNN
K Zeng, S Ding, W Jia - Applied Intelligence, 2019 - Springer
In recent years, artificial intelligence has drawn the attention of the world, and the
contributions of deep learning is enormous. The convolution neural network (CNN) provides …
contributions of deep learning is enormous. The convolution neural network (CNN) provides …
Systems and methods for deep learning microscopy
2019-06-11 Assigned to THE REGENTS OF THE UNIVERSITY OF CALIFORNIA
reassignment THE REGENTS OF THE UNIVERSITY OF CALIFORNIA ASSIGNMENT OF …
reassignment THE REGENTS OF THE UNIVERSITY OF CALIFORNIA ASSIGNMENT OF …
A review of single image super-resolution based on deep learning
N Zhang, ZX WY-C - 2020 - ir.ciomp.ac.cn
Super-resolution (SR) refers to an estimation of high resolution (HR) image from one or
more low resolution (LR) observations of the same scene, usually employing digital image …
more low resolution (LR) observations of the same scene, usually employing digital image …
An unsupervised remote sensing single-image super-resolution method based on generative adversarial network
N Zhang, Y Wang, X Zhang, D Xu, X Wang - IEEE Access, 2020 - ieeexplore.ieee.org
Image super-resolution (SR) technique can improve the spatial resolution of images without
upgrading the imaging system. As a result, SR promotes the development of high resolution …
upgrading the imaging system. As a result, SR promotes the development of high resolution …
[HTML][HTML] RSPCN: Super-resolution of digital elevation model based on recursive sub-pixel convolutional neural networks
R Zhang, S Bian, H Li - ISPRS International Journal of Geo-Information, 2021 - mdpi.com
The digital elevation model (DEM) is known as one kind of the most significant fundamental
geographical data models. The theory, method and application of DEM are hot research …
geographical data models. The theory, method and application of DEM are hot research …
[HTML][HTML] FSRSS-Net: High-resolution mapping of buildings from middle-resolution satellite images using a super-resolution semantic segmentation network
T Zhang, H Tang, Y Ding, P Li, C Ji, P Xu - Remote Sensing, 2021 - mdpi.com
Satellite mapping of buildings and built-up areas used to be delineated from high spatial
resolution (eg, meters or sub-meters) and middle spatial resolution (eg, tens of meters or …
resolution (eg, meters or sub-meters) and middle spatial resolution (eg, tens of meters or …