Article
Environmental Sciences
Jing Zhang, Renjie Zheng, Xu Chen, Zhaolong Hong, Yunsong Li, Ruitao Lu
Summary: In this study, a hyperspectral image super-resolution network based on spectrum-guided attention was proposed to analyze the obtained information from hyperspectral images. The method utilized spectrum-guided attention fusion and high-low frequency separated multi-level feature fusion to improve the performance of super-resolution algorithms. Experimental results on three general hyperspectral datasets showed the advantage of our method compared to existing methods.
Article
Computer Science, Information Systems
Sahar Rahimi Malakshan, Mohammad Saeed Ebrahimi Saadabadi, Moktari Mostofa, Sobhan Soleymani, Nasser M. Nasrabadi
Summary: This research proposes an end-to-end HPE framework assisted by a Face Super-Resolution (FSR) algorithm. The FSR model is designed to enhance the HPE performance. A Multi-Stage Generative Adversarial Network (MSGAN) is utilized to generate super-resolved images aligned for HPE. The proposed method shows superior performance in both visual and HPE metrics on synthetic and real-world LR datasets.
Article
Chemistry, Multidisciplinary
Ning Ouyang, Zhishan Ou, Leping Lin
Summary: In this paper, a new motion compensation method is proposed to design an alignment network based on gated high-low resolution frames. The core idea is to introduce a gating mechanism while using the information of high-low resolution neighboring frames to perform motion compensation adaptively. Compared with existing video super-resolution methods, this method achieves good performance and clearer edge and texture details.
APPLIED SCIENCES-BASEL
(2023)
Article
Automation & Control Systems
Yixian Liu, Yubin Wang, Qiang Yang
Summary: The increasing penetration of distributed renewable generation has brought uncertainties and randomness to power distribution network operation. Accurate and timely awareness of the network operation is crucial, but can be costly. Existing state estimation methods may not converge with incomplete and inaccurate measurements. This article proposes a spatio-temporal estimation generative adversarial network (ST-EGAN) to generate high-resolution pseudo-measurements for accurate state estimation.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Energy & Fuels
Xinglin Liu, Chao Huang, Long Wang, Xiong Luo
Summary: This paper proposes an improved SRPCNN model for PV data recovery, which can better handle data missing issues and achieve better accuracy improvement. Furthermore, the use of a modified whale optimization algorithm to optimize the hyperparameters of the model further enhances the data recovery performance.
Article
Engineering, Electrical & Electronic
Emma J. Reid, Lawrence F. Drummy, Charles A. Bouman, Gregery T. Buzzard
Summary: This paper presents a Multi-resolution Data Fusion algorithm that accurately interpolates low-resolution electron microscope data. The algorithm utilizes small amounts of unpaired high-resolution data to train a neural network denoiser and incorporates a Multi-Agent Consensus Equilibrium problem formulation to balance the denoiser with a forward model agent for fidelity to measured data.
IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING
(2022)
Article
Construction & Building Technology
Beichao Hu, Zeda Yin, Abderrachid Hamrani, Arturo Leon, Dwayne McDaniel
Summary: This paper introduces an innovative super-resolution approach to model the air flow and temperature field in the cold aisle of a data center. The proposed method reconstructs a high-fidelity flow field by using a low-fidelity flow field, significantly reducing the computational time and enabling real-time prediction.
BUILDING AND ENVIRONMENT
(2024)
Article
Chemistry, Analytical
Bong-seok Kim, Youngseok Jin, Jonghun Lee, Sangdong Kim
Summary: This paper introduces a high-efficiency super-resolution FMCW radar algorithm based on FFT, which adaptively selects the number of input samples for distance estimation of targets and achieves similar performance to the conventional MUSIC algorithm while significantly reducing complexity.
Article
Engineering, Electrical & Electronic
Fan-Shuo Tseng, Mantsawee Sanpayao, Tsang-Yi Wang, Ming-Xian Zhong
Summary: This article proposes three high-performance computationally efficient (HPCE) methods for high-resolution frequency estimators based on a modified likelihood function. These methods not only meet the Cramer-Rao lower bound (CRLB) in most cases, but also have lower computational complexity compared to existing approaches.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Electrical & Electronic
Xiantao Cheng, Binyang Xia, Ke Xu, Shaoqian Li
Summary: This paper introduces a novel OFDM receiver architecture that uses low-resolution ADC for oversampling and proposes a solution to address the challenges associated with this architecture. The proposed solution includes the use of a two-phase transmission protocol and Bayesian inference for channel estimation and data detection. Due to the oversampling operation, the proposed receiver can significantly outperform conventional OFDM receivers with perfect quantization.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2021)
Article
Engineering, Civil
Jiawei Shan, Gang Zhang, Chufeng Tang, Hujie Pan, Qiankun Yu, Guanhao Wu, Xiaolin Hu
Summary: In this study, a new distillation method called Focal Distillation is proposed to improve the performance of low-resolution LiDAR detectors by leveraging high-resolution detectors. Extensive experiments show significant improvements on different datasets and models, demonstrating the generalization ability of the proposed method.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Xin Qiao, Chenyang Ge, Youmin Zhang, Yanhui Zhou, Fabio Tosi, Matteo Poggi, Stefano Mattoccia
Summary: Guided depth super-resolution is a technique that aims to restore a high-resolution depth map using a low-resolution depth map and an associated high-resolution RGB image. Current methods still face challenges in restoring precise and sharp edges near depth discontinuities and fine structures. To address this issue, we propose a novel multi-stage depth super-resolution network that progressively reconstructs high-resolution depth maps using explicit and implicit high-frequency information.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2023)
Article
Multidisciplinary Sciences
Gianluca Boo, Edith Darin, Douglas R. Leasure, Claire A. Dooley, Heather R. Chamberlain, Attila N. Lazar, Kevin Tschirhart, Cyrus Sinai, Nicole A. Hoff, Trevon Fuller, Kamy Musene, Arly Batumbo, Anne W. Rimoin, Andrew J. Tatem
Summary: This study develops a Bayesian model to estimate population data at high resolution in five provinces of the Democratic Republic of the Congo. By combining household surveys and building footprints, the authors provide up-to-date population estimates in a country with outdated censuses.
NATURE COMMUNICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Yingqian Wang, Longguang Wang, Gaochang Wu, Jungang Yang, Wei An, Jingyi Yu, Yulan Guo
Summary: This paper proposes a generic mechanism to disentangle the spatial and angular information in light field (LF) images for effective LF image processing. The mechanism uses domain-specific convolutions to disentangle the LF data and task-specific modules to leverage the disentangled features. Three networks are developed based on this mechanism and achieve state-of-the-art performance on spatial super-resolution, angular super-resolution, and disparity estimation tasks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Biochemical Research Methods
Romain F. Laine, Hannah S. Heil, Simao Coelho, Jonathon Nixon-Abell, Angelique Jimenez, Theresa Wiesner, Damian Martinez, Tommaso Galgani, Louise Regnier, Aki Stubb, Gautier Follain, Samantha Webster, Jesse Goyette, Aurelien Dauphin, Audrey Salles, Sian Culley, Guillaume Jacquemet, Bassam Hajj, Christophe Leterrier, Ricardo Henriques
Summary: This article presents an enhanced super-resolution radial fluctuations (eSRRF) method that improves image fidelity and resolution. The method incorporates automated parameter optimization and has been validated across various imaging modalities and biological systems. Additionally, eSRRF has been extended to three dimensions by combining it with multifocus microscopy, enabling live-cell volumetric super-resolution imaging.
Article
Computer Science, Information Systems
Guolong Liu, Jinjin Gu, Junhua Zhao, Fushuan Wen, Gaoqi Liang
INFORMATION SCIENCES
(2020)
Article
Multidisciplinary Sciences
Xinlei Wang, Caomingzhe Si, Jinjin Gu, Guolong Liu, Wenxuan Liu, Jing Qiu, Junhua Zhao
Summary: This study examines the economic impact of COVID-19 on different industries in eastern China, finding that emergency response measures affected all industries, with stricter control leading to a greater decrease in electricity consumption and production. The pandemic outbreak has a negative-lag effect on industries, and there is greater resilience in industries that are less dependent on human mobility for economic production and activities.
SCIENTIFIC REPORTS
(2021)
Article
Energy & Fuels
Jiaqi Ruan, Guolong Liu, Jing Qiu, Gaoqi Liang, Junhua Zhao, Binghao He, Fushuan Wen
Summary: This paper proposes a time-varying algorithm for estimating the price elasticity of demand (PED) in the smart energy system. It also introduces a demand-side smart dynamic pricing mechanism to encourage user participation in demand response programs. Experimental results demonstrate the feasibility of the proposed mechanism in reducing peak-to-average ratio (PAR) without exposure to price risk.
Article
Energy & Fuels
Guolong Liu, Shuwen Zhang, Huan Zhao, Jinjie Liu, Gaoqi Liang, Junhua Zhao, Guangzhong Sun
Summary: This article proposes a data enhancement method and framework to assist wind power forecasting by using super-resolution perception technology to detect and correct errors and missing data in wind power data. The experiments demonstrate the effectiveness of the proposed method and framework.
FRONTIERS IN ENERGY RESEARCH
(2022)
Article
Automation & Control Systems
Guolong Liu, Jinjie Liu, Junhua Zhao, Jing Qiu, Yiru Mao, Zhanxin Wu, Fushuan Wen
Summary: Corporate carbon footprint (CCF) estimation is crucial for achieving carbon neutrality, but current methods may lack comprehensiveness, timeliness, and accuracy. This article proposes a novel method that combines appliance identification and electricity consumption calculation to estimate direct and indirect carbon emissions of factories in real time. Experimental results demonstrate the superiority of the proposed method in appliance identification and its ability to achieve comprehensive and accurate estimation of minute-level CCF.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Multidisciplinary Sciences
Guolong Liu, Jinjie Liu, Yan Bai, Chengwei Wang, Haosheng Wang, Huan Zhao, Gaoqi Liang, Junhua Zhao, Jing Qiu
Summary: Load forecasting is crucial for power systems, but extreme weather events make it more difficult. Due to the lack of relevant public data, it is necessary to release a large-scale load dataset containing extreme weather events.
Article
Computer Science, Artificial Intelligence
Anran Liu, Yihao Liu, Jinjin Gu, Yu Qiao, Chao Dong
Summary: This paper provides a systematic review on recent progress in blind image super-resolution (SR) and proposes a taxonomy to categorize existing methods into three classes based on their degradation modeling and data usage for solving the SR model. This taxonomy helps summarize and differentiate existing methods, and offers insights into current research states and potential research directions. Additionally, the paper summarizes commonly used datasets and previous competitions related to blind image SR, and conducts a comparison of different methods using both synthetic and real testing images, with detailed analysis of their advantages and disadvantages.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Proceedings Paper
Computer Science, Theory & Methods
Zheyuan Li, Yingqi Liu, Xiangyu Chen, Haoming Cai, Jinjin Gu, Yu Qiao, Chao Dong
Summary: Significant progress has been made in single image super-resolution (SISR) recently, but the computational cost is too high for edge devices. To address this issue, the Blueprint Separable Residual Network (BSRN) is proposed, which introduces blueprint separable convolution and more effective attention modules to enhance the model performance. Experimental results show that BSRN achieves outstanding performance among existing efficient SR methods.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022
(2022)
Proceedings Paper
Computer Science, Theory & Methods
Jinjin Gu, Haoming Cai, Chao Dong, Jimmy S. Ren, Radu Timofte, Yuan Gong, Shanshan Lao, Shuwei Shi, Jiahao Wang, Sidi Yang, Tianhe Wu, Weihao Xia, Yujiu Yang, Mingdeng Cao, Cong Heng, Lingzhi Fu, Rongyu Zhang, Yusheng Zhang, Hao Wang, Hongjian Song, Jing Wang, Haotian Fan, Xiaoxia Hou, Ming Sun, Mading Li, Kai Zhao, Kun Yuan, Zishang Kong, Mingda Wu, Chuanchuan Zheng, Marcos Conde, Maxime Burchi, Longtao Feng, Tao Zhang, Yang Li, Jingwen Xu, Haiqiang Wang, Yiting Liao, Junlin Li, Kele Xu, Tao Sun, Yunsheng Xiong, Abhisek Keshari, Komal Komal, Sadbhawana Thakur, Vinit Jakhetiya, Badri N. Subudhi, Hao-Hsiang Yang, Hua-En Chang, Zhi-Kai Huang, Wei-Ting Chen, Sy-Yen Kuo, Saikat Dutta, Sourya Dipta Das, Nisarg A. Shah, Anil Kumar Tiwari
Summary: This paper reports on the NTIRE 2022 challenge on perceptual image quality assessment (IQA), which aims to address the emerging challenge of IQA by perceptual image processing algorithms. The challenge includes two tracks, full-reference IQA and no-reference IQA, and has attracted numerous participants who have achieved remarkable results.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022
(2022)
Proceedings Paper
Computer Science, Theory & Methods
Ren Yang, Radu Timofte, Meisong Zheng, Qunliang Xing, Minglang Qiao, Mai Xu, Lai Jiang, Huaida Liu, Ying Chen, Youcheng Ben, Xiao Zhou, Chen Fu, Pei Cheng, Gang Yu, Junyi Li, Renlong Wu, Zhilu Zhang, Wei Shang, Zhengyao Lv, Yunjin Chen, Mingcai Zhou, Dongwei Ren, Kai Zhang, Wangmeng Zuo, Pavel Ostyakov, Vyal Dmitry, Shakarim Soltanayev, Chervontsev Sergey, Zhussip Magauiya, Xueyi Zou, Youliang Yan, Pablo Navarrete Michelini, Yunhua Lu, Diankai Zhang, Shaoli Liu, Si Gao, Biao Wu, Chengjian Zheng, Xiaofeng Zhang, Kaidi Lu, Ning Wang, Thuong Nguyen Canh, Thong Bach, Qing Wang, Xiaopeng Sun, Haoyu Ma, Shijie Zhao, Junlin Li, Liangbin Xie, Shuwei Shi, Yujiu Yang, Xintao Wang, Jinjin Gu, Chao Dong, Xiaodi Shi, Chunmei Nian, Dong Jiang, Jucai Lin, Zhihuai Xie, Mao Ye, Dengyan Luo, Liuhan Peng, Shengjie Chen, Xin Liu, Qian Wang, Boyang Liang, Hang Dong, Yuhao Huang, Kai Chen, Xingbei Guo, Yujing Sun, Huilei Wu, Pengxu Wei, Yulin Huang, Junying Chen, Ik Hyun Lee, Sunder Ali Khowaja, Jiseok Yoon
Summary: This paper reviews the NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video, introducing the dataset, tracks, participating teams, and final results. The challenge evaluates the state-of-the-art techniques in super-resolution and quality enhancement of compressed video, providing relevant datasets and code resources.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022
(2022)
Article
Computer Science, Artificial Intelligence
Jinjin Gu, Xinlei Wang, Chenang Li, Junhua Zhao, Weijin Fu, Gaoqi Liang, Jing Qiu
Summary: The integrity of images in scientific papers is crucial, but the rapid development of artificial intelligence technology poses a threat as it can be used to generate fake scientific images that are difficult to identify, requiring vigilance from the scientific community.
Proceedings Paper
Computer Science, Artificial Intelligence
Jinjin Gu, Haoming Cai, Chao Dong, Jimmy S. Ren, Yu Qiao, Shuhang Gu, Radu Timofte, Manri Cheon, Sungjun Yoon, Byungyeon Kangg Kang, Junwoo Lee, Qing Zhang, Haiyang Guo, Yi Bin, Yuqing Hou, Hengliang Luo, Jingyu Guo, Zirui Wang, Hai Wang, Wenming Yang, Qingyan Bai, Shuwei Shi, Weihao Xia, Mingdeng Cao, Jiahao Wang, Yifan Chen, Yujiu Yang, Yang Li, Tao Zhang, Longtao Feng, Yiting Liao, Junlin Li, William Thong, Jose Costa Pereira, Ales Leonardis, Steven McDonagh, Kele Xu, Lehan Yang, Hengxing Cai, Pengfei Sun, Seyed Mehdi Ayyoubzadeh, Ali Royat, Sid Ahmed Fezza, Dounia Hammou, Wassim Hamidouche, Sewoong Ahn, Gwangjin Yoon, Koki Tsubota, Hiroaki Akutsu, Kiyoharu Aizawa
Summary: The NTIRE 2021 challenge focused on perceptual image quality assessment tasks using Generative Adversarial Networks (GAN), with 270 registered participants and 13 teams submitting their models for evaluation. Most teams achieved better results than existing IQA methods, with the winning method demonstrating state-of-the-art performance.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
(2021)
Proceedings Paper
Energy & Fuels
Guolong Liu, Jinjie Liu, Junhua Zhao, Fushuan Wen, Yusheng Xue
2020 INTERNATIONAL CONFERENCE ON SMART GRIDS AND ENERGY SYSTEMS (SGES 2020)
(2020)