A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Filters
Perceptual image compression via adaptive block- based super-resolution directed down-sampling
2011
2011 IEEE International Symposium of Circuits and Systems (ISCAS)
In this paper, we propose a novel perceptual image coding scheme via adaptive block-based super-resolution directed down-sampling. ...
The down-sampling process is directed by superresolution, which generates the down-sampled block by minimizing the reconstruction errors between the original macroblock and the one restored by the corresponding ...
CONCLUSION In this paper, a novel perceptual image coding scheme via adaptive block-based super-resolution directed down-sampling is proposed. ...
doi:10.1109/iscas.2011.5937510
dblp:conf/iscas/MaLN11
fatcat:ie62aydpezanpk6mfnsotrthfq
Learning-Based Joint Super-Resolution and Deblocking for a Highly Compressed Image
2015
IEEE transactions on multimedia
Directly performing image super-resolution (SR) to a highly compressed image would also simultaneously magnify the blocking artifacts, resulting in an unpleasing visual experience. ...
A highly compressed image is usually not only of low resolution, but also suffers from compression artifacts (blocking artifact is treated as an example in this paper). ...
Image Super-Resolution There has been a great demand for improving the perceptual quality of images in terms of the spatial resolution enhancement of an image, also known as image super-resolution (SR) ...
doi:10.1109/tmm.2015.2434216
fatcat:xohe6war4jaivibuphvvnzucze
NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
2020
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
The challenge task was to super-resolve an input image with a magnification factor ×16 based on a set of prior examples of low and corresponding high resolution images. ...
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. ...
After each down-sampling or up-sampling layer, a set of residual channel attention blocks are added to learn features at each scale. ...
doi:10.1109/cvprw50498.2020.00254
dblp:conf/cvpr/ZhangGTSDZYGJYK20
fatcat:yvicfxmotjbhfk72f2noujonlq
NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
[article]
2020
arXiv
pre-print
The challenge task was to super-resolve an input image with a magnification factor 16 based on a set of prior examples of low and corresponding high resolution images. ...
They gauge the state-of-the-art in single image super-resolution. ...
After each down-sampling or up-sampling layer, a set of residual channel attention blocks are added to learn features at each scale. ...
arXiv:2005.01056v1
fatcat:6nwj5ilbgbgjnmd6oy435hjdhi
Lifting Wavelet Transform for Super Resolution Image Reconstruction using MATLAB
2013
CVR Journal of Science & Technology
Finally, the samples are interpolated to twice the number of original samples to obtain a super resolution image. ...
Further Set Portioning in Hierarchical Trees (SPIHT) algorithm is applied for image compression as it possess lossless compression, fast encoding/decoding, adaptive nature. ...
Each low resolution image is down sampled using two level biorthogonal filter based discrete wavelet transform and The fusion of decomposed images is done by using fusion rule i.e. ...
doi:10.32377/cvrjst0508
fatcat:je2qa7gt5ndxdgaru44pfdzl7i
HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment
[article]
2020
arXiv
pre-print
content-adaptive suppression modules. ...
This leads to HiFaceGAN, a multi-stage framework containing several nested CSR units that progressively replenish facial details based on the hierarchical semantic guidance extracted from the front-end ...
Blind Face Restoration Blind image restoration [43] [3] [32] aims to directly learn the restoration mapping based on observed samples. ...
arXiv:2005.05005v1
fatcat:lfvg7hhs2zehbaz2l7ake4gtja
Deep Learning-Based Video Coding: A Review and A Case Study
[article]
2019
arXiv
pre-print
DLVC features two deep tools that are both based on convolutional neural network (CNN), namely CNN-based in-loop filter (CNN-ILF) and CNN-based block adaptive resolution coding (CNN-BARC). ...
- and up-sampling, as well as encoding optimizations. ...
CNN-Based Block Adaptive Resolution Coding CNN-BARC is a down-and up-sampling-based coding tool that uses trained CNN models as the down-and up-sampling filters. ...
arXiv:1904.12462v1
fatcat:cgcmwylwnvd67abpl6wders5hy
A Survey on Super Resolution for video Enhancement Using GAN
[article]
2023
arXiv
pre-print
This compilation of various research paper highlights provides a comprehensive overview of recent developments in super-resolution image and video using deep learning algorithms such as Generative Adversarial ...
The studies covered in these summaries provide fresh techniques to addressing the issues of improving image and video quality, such as recursive learning for video super-resolution, novel loss functions ...
Some models exhibited overfitting to specific down sampling methods, while others demonstrated greater stability and yielded similar outcomes in different tests. ...
arXiv:2312.16471v2
fatcat:vri7fii6tzbvbgeylzhdy7lmta
4K-NeRF: High Fidelity Neural Radiance Fields at Ultra High Resolutions
[article]
2022
arXiv
pre-print
Joint training with patch-based sampling further facilitates our method incorporating the supervision from perception oriented regularization beyond pixel wise loss. ...
ability on describing subtle details especially when lifting to a extremely high resolution. ...
The original resolution is 4032 × 3024 while existing NeRF-based methods use 4× down-scaled images (1008 × 756) for training and inference. ...
arXiv:2212.04701v1
fatcat:lmhubprzmre7dpg2juclk33qtq
Deep Learning for Image Super-resolution: A Survey
[article]
2020
arXiv
pre-print
Image Super-Resolution (SR) is an important class of image processing techniques to enhance the resolution of images and videos in computer vision. ...
Recent years have witnessed remarkable progress of image super-resolution using deep learning techniques. ...
Iterative Up-and-down Sampling Super-resolution In order to better capture the mutual dependency of LR-HR image pairs, an efficient iterative procedure named back-projection [12] is incorporated into ...
arXiv:1902.06068v2
fatcat:uequ4heufbcmjojclu2md3xh6m
Multimodal-Boost: Multimodal Medical Image Super-Resolution using Multi-Attention Network with Wavelet Transform
[article]
2022
arXiv
pre-print
Deep learning based single image super resolution (SISR) algorithms has revolutionized the overall diagnosis framework by continually improving the architectural components and training strategies associated ...
with convolutional neural networks (CNN) on low-resolution images. ...
[20] proposed a new method based on video super-resolution. ...
arXiv:2110.11684v2
fatcat:fciyq66b7rcpdibblgbq72jc2y
Generative Adversarial Networks Capabilities for Super-Resolution Reconstruction of Weather Radar Echo Images
2019
Atmosphere
The experimental results showed that the GAN-based method is capable of generating perceptually superior solutions while achieving higher PSNR/SSIM results. ...
Improving the resolution of degraded radar echo images of weather radar systems can aid severe weather forecasting and disaster prevention. ...
Meanwhile, there are research studies focused on radar base data super-resolution without changing the radar hardware or sampling strategy. ...
doi:10.3390/atmos10090555
fatcat:5kvh5feqaff3zmc4q5u2p4eqze
Super-Resolving Compressed Video in Coding Chain
[article]
2021
arXiv
pre-print
In this novel coding chain, the reference-based DCNN learns the direct mapping from low-resolution (LR) compressed video to their high-resolution (HR) clean version at the decoder side. ...
Previous methods for enhancing the resolution of such videos often ignore the inherent interference between resolution loss and compression artifacts, which compromises perceptual video quality. ...
It is known that, at low bit rates, a down-sampled video visually beats the HR video when represented with the same number of bits via compression. ...
arXiv:2103.14247v1
fatcat:36k2xfa7hvgxbofhrlmieglne4
Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training
[article]
2020
arXiv
pre-print
These days, unsupervised super-resolution (SR) has been soaring due to its practical and promising potential in real scenarios. ...
In this paper, we propose a novel domain-distance aware super-resolution (DASR) approach for unsupervised real-world image SR. The domain gap between training data (e.g. Y^g) and testing data (e.g. ...
Introduction Single image super-resolution (SR) aims at reconstructing a high-resolution (HR) image from a low-resolution (LR) observation. ...
arXiv:2004.01178v1
fatcat:rkakgdw43fa4vmvcseurpztgbu
Image Super-resolution via Feature-augmented Random Forest
[article]
2017
arXiv
pre-print
This original-compressed coupled feature sets scheme unifies the unsupervised LSH evaluation on both image super-resolution and content-based image retrieval (CBIR). ...
Recent random-forest (RF)-based image super-resolution approaches inherit some properties from dictionary-learning-based algorithms, but the effectiveness of the properties in RF is overlooked in the literature ...
IMAGE SUPER-RESOLUTION VIA RANDOM FOREST
Image Super-Resolution Image SR attempts to achieve an impressive HR quality image from one or a set of LR images via artistic skills, which has been an active ...
arXiv:1712.05248v1
fatcat:bep2ejds3jfaneuyubh4xgb7ym
« Previous
Showing results 1 — 15 out of 1,386 results