Results 321 to 330 of about 3,028,783 (361)

Image Super-Resolution via Deep Recursive Residual Network

Computer Vision and Pattern Recognition, 2017
Recently, Convolutional Neural Network (CNN) based models have achieved great success in Single Image Super-Resolution (SISR). Owing to the strength of deep networks, these CNN models learn an effective nonlinear mapping from the low-resolution input ...
Ying Tai, Jian Yang, Xiaoming Liu
semanticscholar   +1 more source

Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution

IEEE International Conference on Computer Vision, 2023
Although deep learning-based solutions have achieved impressive reconstruction performance in image super-resolution (SR), these models are generally large, with complex architectures, making them incompatible with low-power devices with many ...
Long Sun, Jiangxin Dong, Jinhui Tang, Jin-shan Pan   +3 more
semanticscholar   +1 more source

Super-resolution for high-resolution displays

2014 IEEE 3rd Global Conference on Consumer Electronics (GCCE), 2014
We propose a super-resolution system for high-resolution displays that decomposes the input image into a structure component and a texture component using total variation regularization. The structure component is processed using a shock filter and the texture component is processed by a pulse enhancement filter. This system requires less computational
Kyohei Goto, Fumiya Nagashima, Tomio Goto, Satoshi Hirano, Masaru Sakurai   +4 more
openaire   +1 more source

Second-Order Attention Network for Single Image Super-Resolution

Computer Vision and Pattern Recognition, 2019
Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and obtained remarkable performance.
Tao Dai, Jianrui Cai, Yongbing Zhang, Shutao Xia, Lei Zhang   +4 more
semanticscholar   +1 more source

One-Step Effective Diffusion Network for Real-World Image Super-Resolution

Neural Information Processing Systems
The pre-trained text-to-image diffusion models have been increasingly employed to tackle the real-world image super-resolution (Real-ISR) problem due to their powerful generative image priors.
Rongyuan Wu, Lingchen Sun, Zhiyuan Ma, Lei Zhang   +3 more
semanticscholar   +1 more source

Implicit Diffusion Models for Continuous Super-Resolution

Computer Vision and Pattern Recognition, 2023
Image super-resolution (SR) has attracted increasing attention due to its widespread applications. However, current SR methods generally suffer from over-smoothing and artifacts, and most work only with fixed magnifications.
Sicheng Gao, Xuhui Liu, Bo-Wen Zeng, Sheng Xu, Yanjing Li, Xiaonan Luo, Jianzhuang Liu, Xiantong Zhen, Baochang Zhang   +8 more
semanticscholar   +1 more source

Depth map super-resolution

2011 IEEE 19th Signal Processing and Communications Applications Conference (SIU), 2011
The objective of this work is to increase the range resolution of time-of-flight (ToF) cameras. Our work aims to produce a super-resolution depth map and reduce the depth error within the whole work volume using a novel multi-exposure data acquisition technique and Projection Onto Convex Sets(POCS) reconstruction.
Murat Gevrekci, Kubilay Pakin
openaire   +1 more source

Enhanced Deep Image Prior for Unsupervised Hyperspectral Image Super-Resolution

IEEE Transactions on Geoscience and Remote Sensing
Depending on a large-scale paired dataset of low-resolution hyperspectral image (LrHSI), high-resolution multispectral image (HrMSI), and corresponding high-resolution hyperspectral image (HrHSI), the supervised paradigm has achieved impressive ...
Jiaxin Li, Ke Zheng, Lianru Gao, Zhu Han, Zhi Li, Jocelyn Chanussot   +5 more
semanticscholar   +1 more source

Model-Informed Multistage Unsupervised Network for Hyperspectral Image Super-Resolution

IEEE Transactions on Geoscience and Remote Sensing
By fusing a low-resolution hyperspectral image (LrMSI) with an auxiliary high-resolution multispectral image (HrMSI), hyperspectral image super-resolution (HISR) can generate a high-resolution hyperspectral image (HrHSI) economically.
Jiaxin Li, Ke Zheng, Lianru Gao, Li Ni, Min Huang, Jocelyn Chanussot   +5 more
semanticscholar   +1 more source

Fast, Accurate, and, Lightweight Super-Resolution with Cascading Residual Network

European Conference on Computer Vision, 2018
In recent years, deep learning methods have been successfully applied to single-image super-resolution tasks. Despite their great performances, deep learning methods cannot be easily applied to real-world applications due to the requirement of heavy ...
Namhyuk Ahn, Byungkon Kang, Kyung-ah Sohn   +2 more
semanticscholar   +1 more source