scholarly journals Style-Based Unsupervised Learning for Real-World Face Image Super-Resolution

2020 ◽  
Author(s):  
Ahmed Cheikh Sidiya ◽  
Xin Li
Keyword(s):  
Unsupervised Learning ◽  
Real World ◽  
Super Resolution ◽  
Image Synthesis ◽  
Face Image ◽  
Quality Improvements ◽  
Training Strategy ◽  
Face Images ◽  
Image Super Resolution ◽  
Single Image Super Resolution

Face image synthesis has advanced rapidly in recent years. However, similar success has not been witnessed in related areas such as face single image super-resolution (SISR). The performance of SISR on real-world low-quality face images remains unsatisfactory. In this paper, we demonstrate how to advance the state-of-the-art in face SISR by leveraging style-based generator in unsupervised settings. For real-world low-resolution (LR) face images, we propose a novel unsupervised learning approach by combining style-based generator with relativistic discriminator. With a carefully designed training strategy, we demonstrate our converges faster and better suppresses artifacts than Bulat’s approach. When trained on an ensemble of high-quality datasets (CelebA, AFLW, LS3D-W, and VGGFace2), we report significant visual quality improvements over other competing methods especially for real-world low-quality face images such as those in Widerface. Additionally, we have verified that both our unsupervised approaches are capable of improving the matching performance of widely used face recognition systems such as OpenFace.

scholarly journals Toward Real-World Single Image Super-Resolution: A New Benchmark and a New Model

2019 ◽  
Author(s):  
Jianrui Cai ◽  
Hui Zeng ◽  
Hongwei Yong ◽  
Zisheng Cao ◽  
Lei Zhang
Keyword(s):  
Real World ◽  
Super Resolution ◽  
Single Image ◽  
New Model ◽  
Image Super Resolution ◽  
Single Image Super Resolution

scholarly journals Real-world single image super-resolution: A brief review

2021 ◽  
Author(s):  
Honggang Chen ◽  
Xiaohai He ◽  
Linbo Qing ◽  
Yuanyuan Wu ◽  
Chao Ren ◽  
...  
Keyword(s):  
Real World ◽  
Super Resolution ◽  
Single Image ◽  
Image Super Resolution ◽  
Single Image Super Resolution

scholarly journals Blind Image Super Resolution Using Deep Unsupervised Learning

Electronics ◽  
2021 ◽  
Vol 10 (21) ◽  
pp. 2591
Author(s):  
Kazuhiro Yamawaki ◽  
YongQing Sun ◽  
Xian-Hua Han
Keyword(s):  
Unsupervised Learning ◽  
Large Scale ◽  
Super Resolution ◽  
Training Data ◽  
Paired Data ◽  
Degradation Models ◽  
Benchmark Datasets ◽  
Image Super Resolution ◽  
Single Image Super Resolution ◽  
Blind Image

The goal of single image super resolution (SISR) is to recover a high-resolution (HR) image from a low-resolution (LR) image. Deep learning based methods have recently made a remarkable performance gain in terms of both the effectiveness and efficiency for SISR. Most existing methods have to be trained based on large-scale synthetic paired data in a fully supervised manner. With the available HR natural images, the corresponding LR images are usually synthesized with a simple fixed degradation operation, such as bicubic down-sampling. Then, the learned deep models with these training data usually face difficulty to be generalized to real scenarios with unknown and complicated degradation operations. This study exploits a novel blind image super-resolution framework using a deep unsupervised learning network. The proposed method can simultaneously predict the underlying HR image and its specific degradation operation from the observed LR image only without any prior knowledge. The experimental results on three benchmark datasets validate that our proposed method achieves a promising performance under the unknown degradation models.

Deep fractal residual network for fast and accurate single image super resolution

2020 ◽  
Vol 398 ◽  
pp. 389-398 ◽  
Author(s):  
Yanghao Zhou ◽  
Jianfeng Dong ◽  
Yubin Yang
Keyword(s):  
Super Resolution ◽  
Single Image ◽  
Residual Network ◽  
Image Super Resolution ◽  
Single Image Super Resolution

scholarly journals Real-Time Environment Monitoring Using a Lightweight Image Super-Resolution Network

2021 ◽  
Vol 18 (11) ◽  
pp. 5890
Author(s):  
Qiang Yu ◽  
Feiqiang Liu ◽  
Long Xiao ◽  
Zitao Liu ◽  
Xiaomin Yang
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Super Resolution ◽  
Model Complexity ◽  
Practical Application ◽  
Single Image ◽  
Feature Maps ◽  
Benchmark Datasets ◽  
Image Super Resolution ◽  
Single Image Super Resolution

Deep-learning (DL)-based methods are of growing importance in the field of single image super-resolution (SISR). The practical application of these DL-based models is a remaining problem due to the requirement of heavy computation and huge storage resources. The powerful feature maps of hidden layers in convolutional neural networks (CNN) help the model learn useful information. However, there exists redundancy among feature maps, which can be further exploited. To address these issues, this paper proposes a lightweight efficient feature generating network (EFGN) for SISR by constructing the efficient feature generating block (EFGB). Specifically, the EFGB can conduct plain operations on the original features to produce more feature maps with parameters slightly increasing. With the help of these extra feature maps, the network can extract more useful information from low resolution (LR) images to reconstruct the desired high resolution (HR) images. Experiments conducted on the benchmark datasets demonstrate that the proposed EFGN can outperform other deep-learning based methods in most cases and possess relatively lower model complexity. Additionally, the running time measurement indicates the feasibility of real-time monitoring.

Compact and progressive network for enhanced single image super-resolution—ComPrESRNet

2021 ◽  
Author(s):  
Vishal Chudasama ◽  
Kishor Upla ◽  
Kiran Raja ◽  
Raghavendra Ramachandra ◽  
Christoph Busch
Keyword(s):  
Super Resolution ◽  
Single Image ◽  
Image Super Resolution ◽  
Single Image Super Resolution
Sign in / Sign up

Export Citation Format

Share Document