Location:
Search - LR images
Search list
Description: super resultion achieved by interpolation. SR image is obtained by registration of several LR images and interpoltation after that step.
Platform: |
Size: 33792 |
Author: xinhui |
Hits:
Description: 输入一帧高分辨率图像，生成低分辨率图像序列的程序-Enter a high-resolution images, the program generates low resolution image sequence
Platform: |
Size: 2048 |
Author: Snow |
Hits:
Description: ：超分辨率(sR)重建技术是利用一幅或多幅低分辨率(LR)图像的信息重建出一幅高分辨率(HR)图像，同时能够
消除由成像器件引入的模糊、噪声。该技术应用领域广泛，已经成为国内外图像处理领域的研究热点之一。介绍了超分
辨率重建技术的基本原理，并分别以单帧和多帧、频域和空域为分类依据，分别阐述了超分辨率重建技术的经典方法，系
统地总结了各种方法的优缺点，提出了超分辨率重建技术可能的研究方向，从而为超分辨率重建相关技术的进一步研究
提供一定的理论基础-Abstract：Super—resolution image reconstruction technique produces a high—resolution image from seve~ low—resolution images，call al—
SO eliminate additive noise and the distinction Which has been come from limited detector of size and optical components．Therefore．it
has been a lot topic in the field of image processing．Introduces the basic principle of super—resolution reconstruction tec hnique，and classifies
the classical method based on single frame and multi frame．the frequency domain and airspace．Systematically summarizes the ad—
van tages an d disadvan tages of various methods and provide theoretical basis for the supe r—resolution reconstruction technique of further
research，and puts forward the research direction of super-resolution reconstruction technique
Platform: |
Size: 355328 |
Author: liuzhao |
Hits:
Description: 改代码主要是把从一帧高分辨率图像产生多帧低分辨率图像-one HR image generates several LR images
Platform: |
Size: 12288 |
Author: wendy |
Hits:
Description: 本文提出，为第一次，一个统一的多图像超分辨率盲法（MISR或SR），单个图像模糊反卷积（二次发射离子束淀积），和多图像模糊反褶积（国际金业）的低分辨率（LR）图像退化通过线性空间不变（LSI）模糊，锯齿，加白高斯噪声（AWGN）。该方法是基于
交替最小化（AM）的一个新的成本函数
对于未知的高分辨率（HR）图像和模糊。
-This paper presents, for the first time, a unified
blind method for multi-image super-resolution (MISR or SR),
single-image blur deconvolution (SIBD), and multi-image blur
deconvolution (MIBD) of low-resolution (LR) images degraded
by linear space-invariant (LSI) blur, aliasing, and additive white
Gaussian noise (AWGN). The proposed approach is based on
alternating minimization (AM) of a new cost function with
respect to the unknown high-resolution (HR) image and blurs.
Platform: |
Size: 2874368 |
Author: wangshuang |
Hits:
Description: The learning-based approaches assume that the lost high
frequency details in LR images can be retrieved and
hallucinated a dictionary of image patch pairs.-The learning-based approaches assume that the lost high
frequency details in LR images can be retrieved and
hallucinated a dictionary of image patch pairs.
Platform: |
Size: 1024 |
Author: Karthik |
Hits: