Single image super resolution aims to enhance image quality with respect to spatial content, which is a fundamental task in computer vision. In this work, we address the task of single frame super resolution with the presence of image degradation, e.g., blur, haze, or rain streaks. Due to the limitations of frame capturing and formation processes, image degradation is inevitable, and the artifacts would be exacerbated by super resolution methods. To address this problem, we propose a dual-branch convolutional neural network to extract base features and recovered features separately. The base features contain local and global information of the input image. On the other hand, the recovered features focus on the degraded regions and are used to remove the degradation. Those features are then fused through a recursive gate module to obtain sharp features for super resolution. By decomposing the feature extraction step into two task-independent streams, the dual-branch model can facilitate the training process by avoiding learning the mixed degradation all-in-one and thus enhance the final high-resolution prediction results. We evaluate the proposed method in three degradation scenarios. Experiments on these scenarios demonstrate that the proposed method performs more efficiently and favorably against the state-of-the-art approaches on benchmark datasets.
Versatile and Efficient Medical Image Super-Resolution Via Frequency-Gated Mamba
Faculty of Engineering and Information Technology, University of Technology Sydney, Australia（工程与信息技术学院，悉尼技术大学，澳大利亚）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China（深圳先进技术研究所，中国科学院，中国）；College of Computer Science and Technology, Qingdao University, China（计算机科学与技术学院，青岛大学，中国）；Faculty of Computer Science and Control Engineering, Shenzhen University of Advanced Technology, China（计算机科学与控制工程学院，深圳先进技术大学，中国）
Spatial-Frequency Gated Swin Transformer for Cross-Sensor Remote Sensing Super-Resolution
Space Applications Centre, ISRO, Ahmedabad, India（印度航天研究组织阿赫迈德亚布德研究中心）；Centre of Studies in Resources Engineering, Indian Institute of Technology Bombay, India（印度理工学院孟买资源工程研究学院）；New L J Institute of Engineering and Technology, Ahmedabad, India（阿赫迈德亚布德新LJ工程与技术学院）；Pandit Deendayal Energy University, Gandhinagar, India（潘迪特·德恩达尔能源大学）；GLS University, Ahmedabad, India（阿赫迈德亚布德GLS大学）
DACESR: Degradation-Aware Conditional Embedding for Real-World Image Super-Resolution
School of Electrical and Information Engineering, Zhengzhou University of Light Industry（郑州轻工业大学电气与信息工程学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；School of Automation, Central South University（中南大学自动化学院）；Intelligent Manufacturing Engineering at Machinery Technology Development Co.,Ltd.（机械技术发展有限公司智能制造工程）；China Academy of Machinery Science and Technology Group Co.,Ltd.（中国机械科学与技术集团有限公司）
SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder
Yau Mathematical Sciences Center, Tsinghua University（清华大学丘成桐数学科学中心）；Hisilicon（海思半导体）；Yanqi Lake Beijing Institute of Mathematical Sciences and Applications（雁栖湖北京数学科学与应用研究院）；State Key Laboratory of Membrane Biology, School of Life Sciences, Tsinghua University（清华大学生命科学学院膜生物学国家重点实验室）
GM-MoE: Low-Light Enhancement with Gated-Mechanism Mixture-of-Experts
Xinjiang University（新疆大学）；Harbin University of Commerce（哈尔滨商业大学）；Changchun University of Science and Technology（长春理工大学）；University of Science and Technology Beijing（北京科技大学）；University of Trento（特伦托大学）
Uncertainty-Guided Adverse Weather Restoration via Gated Transformer Network
School of Automation, Southeast University（东南大学自动化学院）；Chair of Robotics, Artificial Intelligence and Real-time Systems, Technical University of Munich（慕尼黑工业大学机器人、人工智能与实时系统讲席教授组）
PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation
Beihang University（北航）；Beijing University of Posts and Telecommunications（北京邮电大学）；Taishan University（泰山大学）；Nanyang Technological University（南洋理工大学）；Henan University of Science and Technology（河南科技大学）
Semantic-Guided Cross-Sensor Super Resolution of Remote Sensing Images: A Gated Dual Conditioning Flow Matching Model
School of Computing and Augmented Intelligence（计算与增强智能学院）；School of Geographical Sciences and Urban Planning（地理科学与城市规划学院）；Arizona State University（亚利桑那州立大学）
3D Gated Recurrent Fusion for Semantic Scene Completion
The University of Adelaide（阿德莱德大学）；Nanjing University of Science and Technology（南京理工大学）；Northwestern Polytechnical University（西北工业大学）；ETH Zurich（苏黎世联邦理工学院）
Forecasting When to Forecast: Accelerating Diffusion Models with Confidence-Gated Taylor
School of Computer Science, Wuhan University（武汉大学计算机学院）；PaddlePaddle Team, Baidu Inc（百度公司PaddlePaddle团队）；International Joint Innovation Center, The Electromagnetics Academy at Zhejiang University（浙江大学电磁学学院国际联合创新中心）；Yunnan Key Laboratory of Media Convergence（云南媒体融合重点实验室）
Uncertainty-Gated Deformable Network for Breast Tumor Segmentation in MR Images
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；School of Computer Science and Information Engineering, Hefei University of Science（合肥科学技术大学计算机科学与信息工程学院）；Department of Radiology, Southwest Hospital, Army Medical University（西南医院放射科，中国人民解放军陆军军医大学）；School of Electrical and Information Engineering, Tianjin University（天津大学电气与信息工程学院）
MvKSR: Multi-view Knowledge-guided Scene Recovery for Hazy and Rainy Degradation
The Hong Kong Polytechnic University（香港理工大学）；Wuhan University of Technology（武汉理工大学）；Wuhan Baosight Software Co., Ltd（武汉宝信软件有限公司）；Singapore Management University（新加坡管理大学）
RestoreDet: Degradation Equivariant Representation for Object Detection in Low Resolution Images
Shanghai Jiao Tong University（上海交通大学）；University of Texas at Arlington（德克萨斯大学阿灵顿分校）；RIKEN AIP（理化学研究所革新智能综合研究中心）；The University of Tokyo（东京大学）；Innopeak Technology；The University of British Columbia（不列颠哥伦比亚大学）；Shanghai AI Laboratory（上海人工智能实验室）
