In recent years, deep learning-based methods have been successfully applied to the image distortion restoration tasks. However, scenarios that assume a single distortion only may not be suitable for many real-world applications. To deal with such cases, some studies have proposed sequentially combined distortions datasets. Viewing in a different point of combining, we introduce a spatially-heterogeneous distortion dataset in which multiple corruptions are applied to the different locations of each image. In addition, we also propose a mixture of experts network to effectively restore a multi-distortion image. Motivated by the multi-task learning, we design our network to have multiple paths that learn both common and distortion-specific representations. Our model is effective for restoring real-world distortions and we experimentally verify that our method outperforms other models designed to manage both single distortion and multiple distortions.
Mi-Ripple: Restoring Images Degraded by Iterative AI Editing
Miyang Technology (Shanghai) Co., Ltd.(米扬科技(上海)有限公司);Key Laboratory of System Software (Chinese Academy of Sciences)(中国科学院系统软件重点实验室);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);University of Chinese Academy of Sciences(中国科学院大学);Shanghai Jiao Tong University(上海交通大学);Tianjin University(天津大学)
ReviveDiff: A Universal Diffusion Model for Restoring Images in Adverse Weather Conditions
Faculty of Engineering and Information Technology, University of Technology Sydney(工程与信息技术学院,技术悉尼大学);PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering, Nanjing University of Science and Technology(智能感知与高维信息系统教育部重点实验室,计算机科学与工程学院,南京理工大学);Key Laboratory of Artificial Intelligence, Ministry of Education(人工智能教育部重点实验室)
Restoring Images in Adverse Weather Conditions via Histogram Transformer
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院);School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区网络空间安全学院);Guangdong Provincial Key Laboratory of Information Security Technology(广东省信息安全技术重点实验室);Wechat Business Group, Tencent(腾讯微信事业群)
Transparency Distortion Robustness for SOTA Image Segmentation Tasks
Technical University of Darmstadt(达姆施塔特工业大学);Fraunhofer Institute for Computer Graphics Research IGD(弗劳恩霍夫计算机图形学研究所);CGV Institute, Graz University of Technology(格拉茨工业大学CGV研究所)
针对不均匀玻璃或热空气折射导致的空间变化径向畸变,本文提出合成数据增强方法,评估其对 SOTA 分割模型的影响,并发现预训练与扩大模型容量比畸变微调更能缓解性能下降。
Robust registration of medical images in the presence of spatially-varying noise
University of California, San Francisco(加州大学旧金山分校);Weill Institute for Neurosciences(威尔神经科学研究所);Iran Science and Technology University(伊朗科技大学);Sharif University of Technology(谢里夫理工大学)
Hong Kong Polytechnic University(香港理工大学);Harbin Institute of Technology(哈尔滨工业大学);Peng Cheng Lab(鹏程实验室);ETH Zurich(苏黎世联邦理工学院);The Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳))
On the Residual-based Neural Network for Unmodeled Distortions in Coordinate Transformation
Federal University of Uberlandia (UFU)(乌贝兰迪亚联邦大学);Federal Institute of Education, Science and Technology of Santa Catarina (IFSC)(圣卡塔琳娜联邦教育、科学和技术学院);Federal University of Paraná (UFPR)(巴拉那联邦大学);Unisinos University(尤尼西诺斯大学)
Point upsampling networks for single-photon sensing
State Key Laboratory of Autonomous Intelligent Unmanned Systems(自主智能无人系统国家重点实验室);Shanghai Research Institute for Intelligent Autonomous Systems(智能自主系统上海研究院);Tongji University(同济大学);The Department of Structural Engineering(结构工程系);The Department of Control Science and Engineering(控制科学与工程系);College of Mathematics and Computer Science(数学与计算机科学学院)