The Experts below are selected from a list of 70581 Experts worldwide ranked by ideXlab platform
Xiaoou Tang - One of the best experts on this subject based on the ideXlab platform.
-
Image super Resolution using deep convolutional networks
arXiv: Computer Vision and Pattern Recognition, 2014Co-Authors: Chao Dong, Kaiming He, Xiaoou TangAbstract:We propose a deep learning method for single Image super-Resolution (SR). Our method directly learns an end-to-end mapping between the Low/high-Resolution Images. The mapping is represented as a deep convolutional neural network (CNN) that takes the Low-Resolution Image as the input and outputs the high-Resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality, and achieves fast speed for practical on-line usage. We explore different network structures and parameter settings to achieve trade-offs between performance and speed. Moreover, we extend our network to cope with three color channels simultaneously, and show better overall reconstruction quality.
-
learning a deep convolutional network for Image super Resolution
European Conference on Computer Vision, 2014Co-Authors: Chao Dong, Chen Change Loy, Kaiming He, Xiaoou TangAbstract:We propose a deep learning method for single Image super-Resolution (SR). Our method directly learns an end-to-end mapping between the Low/high-Resolution Images. The mapping is represented as a deep convolutional neural network (CNN) [15] that takes the Low-Resolution Image as the input and outputs the high-Resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality, and achieves fast speed for practical on-line usage.
Chunhong Pan - One of the best experts on this subject based on the ideXlab platform.
-
edge directed single Image super Resolution via adaptive gradient magnitude self interpolation
IEEE Transactions on Circuits and Systems for Video Technology, 2013Co-Authors: Lingfeng Wang, Shiming Xiang, Gaofeng Meng, Chunhong PanAbstract:Super-Resolution from a single Image plays an important role in many computer vision systems. However, it is still a challenging task, especially in preserving local edge structures. To construct high-Resolution Images while preserving the sharp edges, an effective edge-directed super-Resolution method is presented in this paper. An adaptive self-interpolation algorithm is first proposed to estimate a sharp high-Resolution gradient field directly from the input Low-Resolution Image. The obtained high-Resolution gradient is then regarded as a gradient constraint or an edge-preserving constraint to reconstruct the high-Resolution Image. Extensive results have shown both qualitatively and quantitatively that the proposed method can produce convincing super-Resolution Images containing complex and sharp features, as compared with the other state-of-the-art super-Resolution algorithms.
Chao Dong - One of the best experts on this subject based on the ideXlab platform.
-
Image super Resolution using deep convolutional networks
arXiv: Computer Vision and Pattern Recognition, 2014Co-Authors: Chao Dong, Kaiming He, Xiaoou TangAbstract:We propose a deep learning method for single Image super-Resolution (SR). Our method directly learns an end-to-end mapping between the Low/high-Resolution Images. The mapping is represented as a deep convolutional neural network (CNN) that takes the Low-Resolution Image as the input and outputs the high-Resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality, and achieves fast speed for practical on-line usage. We explore different network structures and parameter settings to achieve trade-offs between performance and speed. Moreover, we extend our network to cope with three color channels simultaneously, and show better overall reconstruction quality.
-
learning a deep convolutional network for Image super Resolution
European Conference on Computer Vision, 2014Co-Authors: Chao Dong, Chen Change Loy, Kaiming He, Xiaoou TangAbstract:We propose a deep learning method for single Image super-Resolution (SR). Our method directly learns an end-to-end mapping between the Low/high-Resolution Images. The mapping is represented as a deep convolutional neural network (CNN) [15] that takes the Low-Resolution Image as the input and outputs the high-Resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality, and achieves fast speed for practical on-line usage.
Minghsuan Yang - One of the best experts on this subject based on the ideXlab platform.
-
ntire 2018 challenge on single Image super Resolution methods and results
Computer Vision and Pattern Recognition, 2018Co-Authors: Radu Timofte, Shuhang Gu, Luc Van Gool, Lei Zhang, Minghsuan YangAbstract:This paper reviews the 2nd NTIRE challenge on single Image super-Resolution (restoration of rich details in a Low Resolution Image) with focus on proposed solutions and results. The challenge had 4 tracks. Track 1 employed the standard bicubic downscaling setup, while Tracks 2, 3 and 4 had realistic unknown downgrading operators simulating camera Image acquisition pipeline. The operators were learnable through provided pairs of Low and high Resolution train Images. The tracks had 145, 114, 101, and 113 registered participants, resp., and 31 teams competed in the final testing phase. They gauge the state-of-the-art in single Image super-Resolution.
-
ntire 2017 challenge on single Image super Resolution methods and results
Computer Vision and Pattern Recognition, 2017Co-Authors: Radu Timofte, Minghsuan Yang, Luc Van Gool, Lei Zhang, Eirikur Agustsson, Xintao Wang, Yapeng Tian, Ke Yu, Yulun Zhang, Shixiang WuAbstract:This paper reviews the first challenge on single Image super-Resolution (restoration of rich details in an Low Resolution Image) with focus on proposed solutions and results. A new DIVerse 2K Resolution Image dataset (DIV2K) was employed. The challenge had 6 competitions divided into 2 tracks with 3 magnification factors each. Track 1 employed the standard bicubic downscaling setup, while Track 2 had unknown downscaling operators (blur kernel and decimation) but learnable through Low and high res train Images. Each competition had ∽100 registered participants and 20 teams competed in the final testing phase. They gauge the state-of-the-art in single Image super-Resolution.
-
fast and accurate head pose estimation via random projection forests
International Conference on Computer Vision, 2015Co-Authors: Donghoon Lee, Minghsuan YangAbstract:In this paper, we consider the problem of estimating the gaze direction of a person from a Low-Resolution Image. Under this condition, reliably extracting facial features is very difficult. We propose a novel head pose estimation algorithm based on compressive sensing. Head Image patches are mapped to a large feature space using the proposed extensive, yet efficient filter bank. The filter bank is designed to generate sparse responses of color and gradient information, which can be compressed using random projection, and classified by a random forest. Extensive experiments on challenging datasets show that the proposed algorithm performs favorably against the state-of-the-art methods on head pose estimation in Low-Resolution Images degraded by noise, occlusion, and blurring.
Yi Lu Murphey - One of the best experts on this subject based on the ideXlab platform.
-
joint learning sparsifying linear transformation for Low Resolution Image synthesis and recognition
Pattern Recognition, 2017Co-Authors: Yuanxiang Li, Hao Shen, Weidong Xiang, Yi Lu MurpheyAbstract:Many computer vision problems involve exploring the synthesis and classification models that map Images from the observed source space to a target space. Recently, one popular and effective method is to transform Images from both source and target space into a shared single sparse domain, in which a synthesis model is established. Motivated by such a technique, this research attempts to explore an effective and robust linear function that maps the sparse representatio ns of Images from the source space to the target space, and simultaneously develop a linear classifier on such a coupled space with both supervised and semi-supervised learning. In order to capture the sparse structure shared by each class, we represent this mapping using a linear transformation with the constraint of sparsity. The performance of our proposed method is evaluated on several benchmark Image datasets for Low-Resolution faces/digits classification and super-Resolution, and the experimental results verify the effectiveness of the proposed method. HighlightsThis paper presents a method that has the capability of solving two problems simultaneously, Image super-Resolution and classification.The sparse transformation matrix learned by our proposed method could capture task-specific discriminative information of Images that is not easily accessible in the original Images.The proposed learning model has been successfully applied to Low-Resolution Image classification with both supervised and semi-supervised settings.
