Results 251 to 260 of about 3,652,577 (286)

Perceptual Losses for Real-Time Style Transfer and Super-Resolution

European Conference on Computer Vision, 2016
We consider image transformation problems, where an input image is transformed into an output image. Recent methods for such problems typically train feed-forward convolutional neural networks using a per-pixel loss between the output and ground-truth ...
Justin Johnson, Alexandre Alahi, Li Fei-Fei   +2 more
semanticscholar   +1 more source

Accelerating the Super-Resolution Convolutional Neural Network

European Conference on Computer Vision, 2016
As a successful deep model applied in image super-resolution (SR), the Super-Resolution Convolutional Neural Network (SRCNN) [1, 2] has demonstrated superior performance to the previous hand-crafted models either in speed and restoration quality. However,
Chao Dong, Chen Change Loy, Xiaoou Tang
semanticscholar   +1 more source

Dual Aggregation Transformer for Image Super-Resolution

IEEE International Conference on Computer Vision, 2023
Transformer has recently gained considerable popularity in low-level vision tasks, including image super-resolution (SR). These networks utilize self-attention along different dimensions, spatial or channel, and achieve impressive performance.
Zheng Chen, Yulun Zhang, Jinjin Gu, L. Kong, Xiaokang Yang, F. Yu   +5 more
semanticscholar   +1 more source

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

Image Super-Resolution with Non-Local Sparse Attention

Computer Vision and Pattern Recognition, 2021
Both Non-Local (NL) operation and sparse representation are crucial for Single Image Super-Resolution (SISR). In this paper, we investigate their combinations and propose a novel Non-Local Sparse Attention (NLSA) with dynamic sparse attention pattern ...
Yiqun Mei, Yuchen Fan, Yuqian Zhou
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

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

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

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

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