Single image superresolution has been a popular research topic in the last two decades and has recently received a new wave of interest due to deep neural networks. In this paper, we approach this problem from a different perspective. With respect to a downsampled low resolution image, we model a high resolution image as a combination of two components, a deterministic component and a stochastic component. The deterministic component can be recovered from the low-frequency signals in the downsampled image. The stochastic component, on the other hand, contains the signals that have little correlation with the low resolution image. We adopt two complementary methods for generating these two components. While generative adversarial networks are used for the stochastic component, deterministic component reconstruction is formulated as a regression problem solved using deep neural networks. Since the deterministic component exhibits clearer local orientations, we design novel loss functions tailored for such properties for training the deep regression network. These two methods are first applied to the entire input image to produce two distinct high-resolution images. Afterwards, these two images are fused together using another deep neural network that also performs local statistical rectification, which tries to make the local statistics of the fused image match the same local statistics of the groundtruth image. Quantitative results and a user study indicate that the proposed method outperforms existing state-of-the-art algorithms with a clear margin.
SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning
University of Science and Technology of China（中国科学技术大学）；Zhangjiang Laboratory（张江实验室）；The University of Sydney（悉尼大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）
提出 SimFIR 自监督框架，利用 ViT 图像块表示与统一畸变感知预训练任务学习细粒度畸变特征，从而提升鱼眼图像校正性能和真实场景泛化能力。
Leveraging Labelled Data Knowledge: A Cooperative Rectification Learning Network for Semi-supervised 3D Medical Image Segmentation
School of Mechanical Engineering and Automation, Northeastern University（东北大学机械工程与自动化学院）；Australian Institute for Machine Learning, University of Adelaide（阿德莱德大学澳大利亚机器学习研究所）；Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey（萨里大学视觉、语音与信号处理中心）
Geometric Representation Learning for Document Image Rectification
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
University of Science and Technology of China（中国科学技术大学）；Zhangjiang Laboratory（张江实验室）；The University of Adelaide（阿德莱德大学）；Australian Institute for Machine Learning（澳大利亚机器学习研究所）
Dual Diffusion Architecture for Fisheye Image Rectification: Synthetic-to-Real Generalization
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；Beijing Key Laboratory of Advanced Information Science and Network（北京先进信息科学与网络重点实验室）
Cascaded Robust Rectification for Arbitrary Document Images
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence（人机混合增强智能国家级实验室）；National Engineering Research Center for Visual Information and Applications（视觉信息与应用国家工程研究中心）；Institute of Artificial Intelligence and Robotics（人工智能与机器人研究院）；Xi’an Jiaotong University（西安交通大学）；The University of Tokyo（东京大学）
LPTR-AFLNet: Lightweight Integrated Chinese License Plate Rectification and Recognition Network
Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, China Three Gorges University（湖北水利水电工程智能视觉监测重点实验室，中国三峡大学）；College of Computer and Information Technology, China Three Gorges University（计算机与信息学院，中国三峡大学）；Hubei Key Laboratory of Digital Finance Innovation（湖北省数字金融创新重点实验室）；School of Information Engineering, Hubei University of Economics（信息工程学院，湖北经济学院）
