Image super-resolution (SR) methods essentially lead to a loss of some high-frequency (HF) information when predicting high-resolution (HR) images from low-resolution (LR) images without using external references. To address this issue, we additionally utilize online retrieved data to facilitate image SR in a unified deep framework. A novel dual high-frequency recovery network (DHN) is proposed to predict an HR image with three parts: an LR image, an internal inferred HF (IHF) map (HF missing part inferred solely from the LR image) and an external extracted HF (EHF) map. In particular, we infer the HF information based on both the LR image and similar HR references which are retrieved online. For the EHF map, we align the references with affine transformation and then in the aligned references, part of HF signals are extracted by the proposed DHN to compensate for the HF loss. Extensive experimental results demonstrate that our DHN achieves notably better performance than state-of-the-art SR methods.
Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensation
Hefei University of Technology（合肥工业大学）；Hangzhou Dianzi University（杭州电子科技大学）；Jinan University（吉林大学）；South China Agricultural University（华南农业大学）；The University of Tokyo（东京大学）
DualX-VSR: Dual Axial Spatial$\times$Temporal Transformer for Real-World Video Super-Resolution without Motion Compensation
University of Science and Technology of China（中国科学技术大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；Tsinghua University（清华大学）；Sun Yat-sen University（中山大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
BasicAVSR: Arbitrary-Scale Video Super-Resolution via Image Priors and Enhanced Motion Compensation
Faculty of Computing, Harbin Institute of Technology（哈尔滨工业大学计算机学院）；School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；Tianjin Key Laboratory of Machine Learning, College of Intelligence and Computing, Tianjin University（天津机器学习重点实验室，天津大学智能计算学院）
Real-World Scene Recovery for Scattering-Degraded Images Using Spatial and Frequency Priors
College of Artificial Intelligence, Southwest University（西南大学人工智能学院）；School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University（深圳大学医学院生物医学工程学院）；School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University（中山大学深圳校区计算机科学与技术学院）；ETcTI, University Politehnica Timisoara（蒂森堡大学ETcTI学院）；College of Computing and Data Science, Nanyang Technological University (NTU)（南洋理工大学计算机与数据科学学院）
Prototype-Based Information Compensation Network for Multi-Source Remote Sensing Data Classification
State Key Laboratory of Physical Oceanography, Ocean University of China（海洋大学物理海洋国家重点实验室）；Department of Electrical and Computer Engineering, Mississippi State University（密苏里州立大学电气与计算机工程系）
HiMo: High-Speed Objects Motion Compensation in Point Clouds
Division of Robotics, Perception, and Learning, KTH Royal Institute of Technology（机器人、感知与学习系，皇家理工学院）；Scania Group（斯堪尼亚集团）；Autonomous Transport Solutions Lab, Scania Group（自主运输解决方案实验室，斯堪尼亚集团）
