Search - Map based Image super resolution

Search - Map based Image super resolution - List

[File Format] 4 DL : 0: 基于MAP的红外图像超分辨率技术研究的硕士论文，文中主要采用最大后验概率完成超分辨率算法的图像重建。-MAP-based infrared image super-resolution technology research master' s thesis, the main use of maximum a posteriori probability of the completion of super-resolution image reconstruction algorithm.
Date : 2025-07-11 Size : 1.81mb User : 路月
[File Format] 5 DL : 0: 基于MAP算法的图像超分辨率重构技术研究硕士论文，文中介绍了超分辨率重建的理论基础与数学模型，基于卡尔曼滤波的序列图像运动估计及基于MAP的超分辨率重建的具体过程。-Algorithm based on MAP Super-Resolution Reconstruction of Image Technology master' s thesis paper introduces the theory of super-resolution reconstruction of the foundation and the mathematical model, based on Kalman filtering image sequences motion estimation and MAP-based super-resolution reconstruction of the specific process.
Date : 2025-07-11 Size : 2.49mb User : 路月
[Multimedia Develop] map_based_image_SR DL : 0: Map based Image super resolution
Date : 2025-07-11 Size : 343kb User : Ashish
[Graph program] 1 DL : 0: 红外图像超分辨率重建仿真研究硕士论文，运用matlab语言进行了基于lX1和2X2两种微扫描工作模式的微位移、反演解析、POCS等三种重建算法的仿真实验，有效地解决了由于欠采样所引起的模糊效应-Super-resolution infrared image reconstruction simulation pp matlab language use and 2X2 based lX1 two micro-micro-scanning mode of displacement, inversion analysis, POCS reconstruction algorithm for the simulation of three such experiments, due to less effective solution the blurring effect caused by sampling
Date : 2025-07-11 Size : 4.62mb User : 锦子
[GDI-Bitmap] MAP DL : 0: 基于map的图像超分辨率的重构算法,用matlab来实现,非常实用-Image super-resolution reconstruction algorithm based on the map, using matlab to achieve very practical
Date : 2025-07-11 Size : 1kb User : 陈天昊
[AI-NN-PR] FaceRecognitionBased-OnDeepLearning DL : 0: 本文运用深度神经网络的方法克服姿态变量和图像分辨率的影响,提出了一种多姿态的人脸超分辨识别算法并在实验数据集上获得了良好的性能表现。另外本文利用深度信念网络探索正面人脸图像和侧面人脸图像的映射,方法放松了深度信念网络的输入也输出之间绝对相等,而只是保证其高层含义上的相等。实验表明了使用深度信念网络可以学习到侧面人脸图像到正面人脸图像的一个全局映射,但是丢失了个体细节差异。本文还提出了基于深度网络保持姿态邻域进行姿态分类的方法,在学习过程中,我们保证了同一个姿态下的人脸图像应该与同一姿态下的多张图像互为邻居。实验证明了,我们的方法在用于姿态分类具有非常良好的性能,但是也发现学习过程中,那些与区别个体的信息逐渐丢失了,这也导致了直接运用非线性近邻元分析的特征的人脸识别的性能不佳。-In this paper, the neural network approach to overcome the depth of variables that affect the attitude and image resolution , proposed a multi-pose face recognition algorithms and super-resolution experimental data set obtained in a good performance. Also this paper to explore the depth of belief network mapping frontal face image and profile face images , the method of absolute equality between the input relax depth of belief networks is also output , but only to ensure equal meaning on its top . Experimental results show that the use of deep belief networks can learn to face image to the side of the front face of a global image map , but lost the details of individual differences . This paper also proposes to maintain posture neighborhood depth network-based gesture classification methods in the learning process , we ensure that the face image under the same gesture with multiple images should be under the same attitude are neighbors . Experiment proves that our method for gesture cl
Date : 2025-07-11 Size : 9.27mb User : cen
[Other] MAP DL : 0: 基于最大后验概率的超分辨图像复原，能够较好的实现频谱外推，实验结果正确-Super-resolution image restoration based on maximum posterior probability, it is possible to achieve a better spectrum extrapolation, experimental results are correct
Date : 2025-07-11 Size : 5kb User : 李思萌
[Program doc] paper3 DL : 0: 基于MAP的单帧字符图像超分辨率重建-Single frame character image super-resolution reconstruction based on MAP
Date : 2025-07-11 Size : 3.98mb User : wang
[Picture Viewer] ltamebsolve DL : 0: In this paper, we propose a multi-sensor super-resolution framework for hybrid imaging to super-resolve data one modality by taking advantage of additional guidance images of a complementary modality. This concept is applied to hybrid 3-D range imaging in image-guided surgery, where high-quality photomet- ric data is exploited to enhance range images of low spatial resolution. We formulate super-resolution based on the maximum a-posteriori (MAP) principle a-In this paper, we propose a multi-sensor super-resolution framework for hybrid imaging to super-resolve data one modality by taking advantage of additional guidance images of a complementary modality. This concept is applied to hybrid 3-D range imaging in image-guided surgery, where high-quality photomet- ric data is exploited to enhance range images of low spatial resolution. We formulate super-resolution based on the maximum a-posteriori (MAP) principle a
Date : 2025-07-11 Size : 3.25mb User : yangs