Although most of the existing image super-resolution(SR)methods have achieved superior performance,contrastive learning for high-level tasks has not been fully utilized in the existing image SR methods based on deep l...Although most of the existing image super-resolution(SR)methods have achieved superior performance,contrastive learning for high-level tasks has not been fully utilized in the existing image SR methods based on deep learning.This work focuses on two well-known strategies developed for lightweight and robust SR,i.e.,contrastive learning and feedback mechanism,and proposes an integrated solution called a split-based feedback network(SPFBN).The proposed SPFBN is based on a feedback mechanism to learn abstract representations and uses contrastive learning to explore high information in the representation space.Specifically,this work first uses hidden states and constraints in recurrent neural network(RNN)to implement a feedback mechanism.Then,use contrastive learning to perform representation learning to obtain high-level information by pushing the final image to the intermediate images and pulling the final SR image to the high-resolution image.Besides,a split-based feedback block(SPFB)is proposed to reduce model redundancy,which tolerates features with similar patterns but requires fewer parameters.Extensive experimental results demonstrate the superiority of the proposed method in comparison with the state-of-the-art methods.Moreover,this work extends the experiment to prove the effectiveness of this method and shows better overall reconstruction quality.展开更多
Previous deep learning-based super-resolution(SR)methods rely on the assumption that the degradation process is predefined(e.g.,bicubic downsampling).Thus,their performance would suffer from deterioration if the real ...Previous deep learning-based super-resolution(SR)methods rely on the assumption that the degradation process is predefined(e.g.,bicubic downsampling).Thus,their performance would suffer from deterioration if the real degradation is not consistent with the assumption.To deal with real-world scenarios,existing blind SR methods are committed to estimating both the degradation and the super-resolved image with an extra loss or iterative scheme.However,degradation estimation that requires more computation would result in limited SR performance due to the accumulated estimation errors.In this paper,we propose a contrastive regularization built upon contrastive learning to exploit both the information of blurry images and clear images as negative and positive samples,respectively.Contrastive regularization ensures that the restored image is pulled closer to the clear image and pushed far away from the blurry image in the representation space.Furthermore,instead of estimating the degradation,we extract global statistical prior information to capture the character of the distortion.Considering the coupling between the degradation and the low-resolution image,we embed the global prior into the distortion-specific SR network to make our method adaptive to the changes of distortions.We term our distortion-specific network with contrastive regularization as CRDNet.The extensive experiments on synthetic and realworld scenes demonstrate that our lightweight CRDNet surpasses state-of-the-art blind super-resolution approaches.展开更多
Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artif...Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning（MRDL） model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method（APPM）. The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.展开更多
针对基于稀疏重建的图像超分辨率（SR）算法一般需要外部训练样本,重建质量取决于待重建图像与训练样本的相似度的问题,提出一种基于局部回归模型的图像超分辨率重建算法。利用局部图像结构会在不同的图像尺度对应位置重复出现的事实,...针对基于稀疏重建的图像超分辨率（SR）算法一般需要外部训练样本,重建质量取决于待重建图像与训练样本的相似度的问题,提出一种基于局部回归模型的图像超分辨率重建算法。利用局部图像结构会在不同的图像尺度对应位置重复出现的事实,建立从低到高分辨率图像块的非线性映射函数一阶近似模型用于超分辨率重建。其中,非线性映射函数的先验模型是直接对输入图像及其低频带图像的对应位样本块对通过字典学习的方法得到。重建图像块时利用图像中的非局部自相似性,对多个非局部自相似块分别应用一阶回归模型,加权综合得到高分辨率图像块。实验结果表明,该算法重建的图像与同样利用图像具有自相似性的相关超分辨率算法相比,峰值信噪比（PSNR）平均提高0.3~1.1 d B,主观重建效果亦有明显提高。展开更多
目的行人重识别旨在解决多个非重叠摄像头下行人的查询和识别问题。在很多实际的应用场景中,监控摄像头获取的是低分辨率行人图像,而现有的许多行人重识别方法很少关注真实场景中低分辨率行人相互匹配的问题。为研究该问题,本文收集并...目的行人重识别旨在解决多个非重叠摄像头下行人的查询和识别问题。在很多实际的应用场景中,监控摄像头获取的是低分辨率行人图像,而现有的许多行人重识别方法很少关注真实场景中低分辨率行人相互匹配的问题。为研究该问题,本文收集并标注了一个新的基于枪球摄像头的行人重识别数据集,并基于此设计了一种低分辨率行人重识别模型来提升低分辨率行人匹配性能。方法该数据集由部署在3个不同位置的枪机摄像头和球机摄像头收集裁剪得到,最终形成包含200个有身份标签的行人和320个无身份标签的行人重识别数据集。与同类其他数据集不同,该数据集为每个行人同时提供高分辨率和低分辨率图像。针对低分辨率下的行人匹配难题,本文提出的基准模型考虑了图像超分、行人特征学习以及判别3个方面因素,并设计了相应的超分模块、特征学习模块和特征判别器模块,分别完成低分辨率图像超分、行人特征学习以及行人特征判断。结果提出的基准模型在枪球行人重识别数据集上的实验表明,对比于经典的行人重识别模型,新基准模型在平均精度均值(mean average precision,mAP)和Rank-1指标上分别提高了3.1%和6.1%。结论本文构建了典型的低分辨率行人重识别数据集,为研究低分辨率行人重识别问题提供了重要的数据来源,并基于该数据集研究了低分辨率下行人重识别基础方法。研究表明,提出的基准方法能够有效地解决低分辨行人匹配问题。展开更多
基金the National Key R&D Program of China(No.2019YFB1405900)the National Natural Science Foundation of China(No.62172035,61976098)。
文摘Although most of the existing image super-resolution(SR)methods have achieved superior performance,contrastive learning for high-level tasks has not been fully utilized in the existing image SR methods based on deep learning.This work focuses on two well-known strategies developed for lightweight and robust SR,i.e.,contrastive learning and feedback mechanism,and proposes an integrated solution called a split-based feedback network(SPFBN).The proposed SPFBN is based on a feedback mechanism to learn abstract representations and uses contrastive learning to explore high information in the representation space.Specifically,this work first uses hidden states and constraints in recurrent neural network(RNN)to implement a feedback mechanism.Then,use contrastive learning to perform representation learning to obtain high-level information by pushing the final image to the intermediate images and pulling the final SR image to the high-resolution image.Besides,a split-based feedback block(SPFB)is proposed to reduce model redundancy,which tolerates features with similar patterns but requires fewer parameters.Extensive experimental results demonstrate the superiority of the proposed method in comparison with the state-of-the-art methods.Moreover,this work extends the experiment to prove the effectiveness of this method and shows better overall reconstruction quality.
基金supported by the National Natural Science Foundation of China(61971165)the Key Research and Development Program of Hubei Province(2020BAB113)。
文摘Previous deep learning-based super-resolution(SR)methods rely on the assumption that the degradation process is predefined(e.g.,bicubic downsampling).Thus,their performance would suffer from deterioration if the real degradation is not consistent with the assumption.To deal with real-world scenarios,existing blind SR methods are committed to estimating both the degradation and the super-resolved image with an extra loss or iterative scheme.However,degradation estimation that requires more computation would result in limited SR performance due to the accumulated estimation errors.In this paper,we propose a contrastive regularization built upon contrastive learning to exploit both the information of blurry images and clear images as negative and positive samples,respectively.Contrastive regularization ensures that the restored image is pulled closer to the clear image and pushed far away from the blurry image in the representation space.Furthermore,instead of estimating the degradation,we extract global statistical prior information to capture the character of the distortion.Considering the coupling between the degradation and the low-resolution image,we embed the global prior into the distortion-specific SR network to make our method adaptive to the changes of distortions.We term our distortion-specific network with contrastive regularization as CRDNet.The extensive experiments on synthetic and realworld scenes demonstrate that our lightweight CRDNet surpasses state-of-the-art blind super-resolution approaches.
文摘Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning（MRDL） model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method（APPM）. The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.
文摘针对基于稀疏重建的图像超分辨率（SR）算法一般需要外部训练样本,重建质量取决于待重建图像与训练样本的相似度的问题,提出一种基于局部回归模型的图像超分辨率重建算法。利用局部图像结构会在不同的图像尺度对应位置重复出现的事实,建立从低到高分辨率图像块的非线性映射函数一阶近似模型用于超分辨率重建。其中,非线性映射函数的先验模型是直接对输入图像及其低频带图像的对应位样本块对通过字典学习的方法得到。重建图像块时利用图像中的非局部自相似性,对多个非局部自相似块分别应用一阶回归模型,加权综合得到高分辨率图像块。实验结果表明,该算法重建的图像与同样利用图像具有自相似性的相关超分辨率算法相比,峰值信噪比（PSNR）平均提高0.3~1.1 d B,主观重建效果亦有明显提高。
文摘目的行人重识别旨在解决多个非重叠摄像头下行人的查询和识别问题。在很多实际的应用场景中,监控摄像头获取的是低分辨率行人图像,而现有的许多行人重识别方法很少关注真实场景中低分辨率行人相互匹配的问题。为研究该问题,本文收集并标注了一个新的基于枪球摄像头的行人重识别数据集,并基于此设计了一种低分辨率行人重识别模型来提升低分辨率行人匹配性能。方法该数据集由部署在3个不同位置的枪机摄像头和球机摄像头收集裁剪得到,最终形成包含200个有身份标签的行人和320个无身份标签的行人重识别数据集。与同类其他数据集不同,该数据集为每个行人同时提供高分辨率和低分辨率图像。针对低分辨率下的行人匹配难题,本文提出的基准模型考虑了图像超分、行人特征学习以及判别3个方面因素,并设计了相应的超分模块、特征学习模块和特征判别器模块,分别完成低分辨率图像超分、行人特征学习以及行人特征判断。结果提出的基准模型在枪球行人重识别数据集上的实验表明,对比于经典的行人重识别模型,新基准模型在平均精度均值(mean average precision,mAP)和Rank-1指标上分别提高了3.1%和6.1%。结论本文构建了典型的低分辨率行人重识别数据集,为研究低分辨率行人重识别问题提供了重要的数据来源,并基于该数据集研究了低分辨率下行人重识别基础方法。研究表明,提出的基准方法能够有效地解决低分辨行人匹配问题。
