Filters








14,313 Hits in 3.6 sec

Deep Learning-based Face Super-Resolution: A Survey [article]

Junjun Jiang, Chenyang Wang, Xianming Liu, Jiayi Ma
2021 arXiv   pre-print
image super-resolution problem.  ...  A curated list of papers and resources to face super-resolution are available at  ...  Joint Face Completion and Super-Resolution. Both low-resolution and occlusion or shadowing always coexist in the real-world face images.  ... 
arXiv:2101.03749v2 fatcat:q56d2mpn4rfyzmi5fo36d2ecja

AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results [article]

Pengxu Wei, Hannan Lu, Radu Timofte, Liang Lin, Wangmeng Zuo, Zhihong Pan, Baopu Li, Teng Xi, Yanwen Fan, Gang Zhang, Jingtuo Liu, Junyu Han (+64 others)
2020 arXiv   pre-print
The goal is to attract more attention to realistic image degradation for the SR task, which is much more complicated and challenging, and contributes to real-world image super-resolution applications.  ...  This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.  ...  ALONG The ALONG team proposed Dual Path Network with high frequency guided for real-world image Super-Resolution.  ... 
arXiv:2009.12072v1 fatcat:7cwsjfhqa5cf7avfvdabpmxrda

AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results [article]

Andreas Lugmayr, Martin Danelljan, Radu Timofte, Manuel Fritsche, Shuhang Gu, Kuldeep Purohit, Praveen Kandula, Maitreya Suin, A N Rajagopalan, Nam Hyung Joon, Yu Seung Won, Guisik Kim, Dokyeong Kwon, Chih-Chung Hsu, Chia-Hsiang Lin (+6 others)
2019 arXiv   pre-print
This paper reviews the AIM 2019 challenge on real world super-resolution. It focuses on the participating methods and final results.  ...  The challenge addresses the real world setting, where paired true high and low-resolution images are unavailable.  ...  [23] , that allows for quantitative benchmarking of real-world super-resolution approaches.  ... 
arXiv:1911.07783v2 fatcat:ik7qykxi35bp7lzvp2pf5o2iny

Learning Frequency-aware Dynamic Network for Efficient Super-Resolution [article]

Wenbin Xie, Dehua Song, Chang Xu, Chunjing Xu, Hui Zhang, Yunhe Wang
2021 arXiv   pre-print
Since pixels or image patches belong to low-frequency areas contain relatively few textural details, this dynamic network will not affect the quality of resulting super-resolution images.  ...  Deep learning based methods, especially convolutional neural networks (CNNs) have been successfully applied in the field of single image super-resolution (SISR).  ...  Introduction Single image super resolution (SISR) receives lowresolution images and outputs their high-resolution counterparts, which is widely used in real-world applications such as mobile phone, surveillance  ... 
arXiv:2103.08357v2 fatcat:vnwyt7rdvnbk7gvf4zm7nnleou

Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training [article]

Yunxuan Wei, Shuhang Gu, Yawei Li, Longcun Jin
2020 arXiv   pre-print
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.  ...  X^r in the real-world LR domain Y^r, and then utilizing the pseudo pairs {Y^g, X^r} for training in a supervised manner.  ...  In this paper, we propose a Domain-distance Aware Super-resolution (DASR) framework for real-world image super-resolution.  ... 
arXiv:2004.01178v1 fatcat:rkakgdw43fa4vmvcseurpztgbu

Edge and Identity Preserving Network for Face Super-Resolution [article]

Jonghyun Kim, Gen Li, Inyong Yun, Cheolkon Jung, Joongkyu Kim
2020 arXiv   pre-print
Thus, we propose a novel Edge and Identity Preserving Network for Face Super-Resolution Network, named as EIPNet, which minimizes the distortion by utilizing a lightweight edge block and identity information  ...  The proposed methods facilitate our super-resolution network to elaborately restore facial components and generate enhanced 8x scaled super-resolution images with a lightweight network structure.  ...  However, the network needs extra labels (e.g. guiding face images) to train the network and it is difficult to obtain the labels in the real-world. III. PROPOSED METHOD A.  ... 
arXiv:2008.11977v1 fatcat:tvjcpnbmbzd2nbpakhksvkotwy

Geometry Enhancements from Visual Content: Going Beyond Ground Truth [article]

Liran Azaria, Dan Raviv
2022 arXiv   pre-print
We present state-of-the-art results for depth super-resolution tasks and as well as visually attractive, enhanced generated 3D models.  ...  This work presents a new cyclic architecture that extracts high-frequency patterns from images and re-insert them as geometric features.  ...  Color guided depth super-resolution Images provide important details for inferring the geometry. The direction of the normal, for example, is correlated to color changes in the image [31] .  ... 
arXiv:2012.08248v3 fatcat:23cat6kjf5dgbcjpj5nlwdpnvu

Multi-modal Deep Guided Filtering for Comprehensible Medical Image Processing [article]

Bernhard Stimpel, Christopher Syben, Franziska Schirrmacher, Philipp Hoelter, Arnd Dörfler, Andreas Maier
2019 arXiv   pre-print
We investigate the performance based on two popular tasks: image super resolution and denoising.  ...  Consequently, we propose the use of the locally linear guided filter in combination with a learned guidance map for general purpose medical image processing.  ...  We demonstrate this based on two popular tasks in natural and medical imaging processing: image super resolution (SR) [20] , [21] , [22] and denoising [23] , [24] , [25] .  ... 
arXiv:1911.07731v1 fatcat:xwvcuyv5fjde3nkmprfacedfje

Reference-based Video Super-Resolution Using Multi-Camera Video Triplets [article]

Junyong Lee and Myeonghee Lee and Sunghyun Cho and Seungyong Lee
2022 arXiv   pre-print
We also propose a two-stage training strategy fully utilizing video triplets in the proposed dataset for real-world 4x video super-resolution.  ...  We propose the first reference-based video super-resolution (RefVSR) approach that utilizes reference videos for high-fidelity results.  ...  Acknowledgments We thank Hyeongseok Son for helpful discussions and Jihye Kim and Anna Choi for their help in collecting the RealMCVSR dataset.  ... 
arXiv:2203.14537v1 fatcat:zzcc3faupvg7ndp2apyexfogti

NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results [article]

Andreas Lugmayr, Martin Danelljan, Radu Timofte, Namhyuk Ahn, Dongwoon Bai, Jie Cai, Yun Cao, Junyang Chen, Kaihua Cheng, SeYoung Chun, Wei Deng, Mostafa El-Khamy (+34 others)
2020 arXiv   pre-print
This paper reviews the NTIRE 2020 challenge on real world super-resolution. It focuses on the participating methods and final results.  ...  The challenge addresses the real world setting, where paired true high and low-resolution images are unavailable.  ...  Frequency Separation Network for Real World Super-Resolution Team Leader: Yuanbo Zhou (webbozhou@gmail.com) Members: Yuanbo Zhou,Fuzhou University Tong Tong, Fuzhou University, Imperial Vision Technology  ... 
arXiv:2005.01996v1 fatcat:ewngd7chdve3fbvwis32v64ruq

Frame and Feature-Context Video Super-Resolution [article]

Bo Yan, Chuming Lin, Weimin Tan
2019 arXiv   pre-print
For video super-resolution, current state-of-the-art approaches either process multiple low-resolution (LR) frames to produce each output high-resolution (HR) frame separately in a sliding window fashion  ...  In this paper, we propose a fully end-to-end trainable frame and feature-context video super-resolution (FFCVSR) network that consists of two key sub-networks: local network and context network, where  ...  as a great deal of separate multi-frame super-resolution subtasks.  ... 
arXiv:1909.13057v1 fatcat:yqqyeeukojevxh7mt6nmgscavq

Frame and Feature-Context Video Super-Resolution

Bo Yan, Chuming Lin, Weimin Tan
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
For video super-resolution, current state-of-the-art approaches either process multiple low-resolution (LR) frames to produce each output high-resolution (HR) frame separately in a sliding window fashion  ...  are constantly accumulated to the subsequent frames.In this paper, we propose a fully end-to-end trainable frame and feature-context video super-resolution (FFCVSR) network that consists of two key sub-networks  ...  as a great deal of separate multi-frame super-resolution subtasks.  ... 
doi:10.1609/aaai.v33i01.33015597 fatcat:l2cikopu6bcuzi3ocetrmtx6ke

A discriminative self‐attention cycle GAN for face super‐resolution and recognition

Xiaoguang Li, Ning Dong, Jianglu Huang, Li Zhuo, Jiafeng Li
2021 IET Image Processing  
A discriminative self-attention cycle generative adversarial network is proposed for real-world face image super-resolution.  ...  Most image superresolution methods adopt paired high-quality and its interpolated low-resolution version to train the super-resolution network.  ...  [11] added another network for an adaptive super-resolution of real images.  ... 
doi:10.1049/ipr2.12250 fatcat:f2aecfugkngrdcjddnccow7jpu

Editorial: Introduction to the Issue on Deep Learning for Image/Video Restoration and Compression

A. Murat Tekalp, Michele Covell, Radu Timofte, Chao Dong
2021 IEEE Journal on Selected Topics in Signal Processing  
("Accurate and Lightweight Image Super-Resolution with Model-Guided Deep Unfolding Network") propose an explainable approach toward SISR named model-guided deep unfolding network (MoG-DUN).  ...  Structurally, MSWSR is composed of one CNN part for low frequencies and one extendable RNN part for high frequencies and multiscale SR. A side window kernel is proposed for efficiency.  ... 
doi:10.1109/jstsp.2021.3053364 fatcat:hjo5pvw6lvgpfga2wfq4vpaq3q

Dual-Camera Super-Resolution with Aligned Attention Modules [article]

Tengfei Wang, Jiaxin Xie, Wenxiu Sun, Qiong Yan, Qifeng Chen
2021 arXiv   pre-print
To bridge the domain gaps between real-world images and the training images, we propose a self-supervised domain adaptation strategy for real-world images.  ...  We present a novel approach to reference-based super-resolution (RefSR) with the focus on dual-camera super-resolution (DCSR), which utilizes reference images for high-quality and high-fidelity results  ...  We thank Hao Ouyang and anonymous reviewers for helpful discussions and suggestions.  ... 
arXiv:2109.01349v2 fatcat:t75spcg4yjdgnaln2aryd57y3a
« Previous Showing results 1 — 15 out of 14,313 results