专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

EP2979242B1 METHOD AND APPARATUS FOR GENERATING A SUPER-RESOLVED IMAGE FROM A SINGLE IMAGE 有权
标题翻译：用于从单个图像生成超分辨率图像的方法和设备
公开(公告)号：EP2979242B1
公开(公告)日：2018-01-10
申请号：EP14713103.1
申请日：2014-03-26
申请人： Thomson Licensing
发明人： DEAMO, Alberto , SALVADOR MARCOS, Jordi , KOCHALE, Axel
IPC分类号： G06T3/40
CPC分类号： G06T3/4053 , G06K9/6215 , G06K2009/6213 , G06T3/4092 , G06T7/13 , G06T7/73 , G06T2207/20201
摘要： Known methods for generating super-resolved images from single input images have various disadvantages. An improved method for generating a super-resolved image from a single low-resolution input image comprises up-scaling the input image to generate an initial version of the super-resolved image, searching, for each patch of the low-resolution input image, similar low-resolution patches in first search windows within down-sampled versions of the input image, and determining, in less down-sampled versions of the input image, high-resolution patches that correspond to the similar low-resolution patches. The determined high-resolution patches are cropped, a second search window is determined in the initial version of the super-resolved image, and a best-matching position for each cropped high-resolution patch is searched within the second search window. Finally, each cropped high-resolution patch is added to the super-resolved image at its respective best-matching position.

2. 发明授权

EP2989607B1 METHOD AND DEVICE FOR PERFORMING SUPER-RESOLUTION ON AN INPUT IMAGE 有权
公开(公告)号：EP2989607B1
公开(公告)日：2019-01-09
申请号：EP14722615.3
申请日：2014-04-25
申请人： Thomson Licensing
发明人： PEREZ PELLITERO, Eduardo , SALVADOR MARCOS, Jordi , KOCHALE, Axel
IPC分类号： G06T3/40

3. 发明公开

EP3167428A1 METHOD AND APPARATUS FOR UP-SCALING AN IMAGE 审中-公开
标题翻译：用于放大图像的方法和设备
公开(公告)号：EP3167428A1
公开(公告)日：2017-05-17
申请号：EP15732284.3
申请日：2015-07-01
申请人： Thomson Licensing
发明人： GANDOLPH, Dirk , SALVADOR MARCOS, Jordi , PUTZKE-ROEMING, Wolfram , KOCHALE, Axel
IPC分类号： G06T3/40
CPC分类号： G06T3/4053 , G06T5/50
摘要： A method and an apparatus (20) for up-scaling an input image (12) are described, wherein a cross-scale self-similarity matching using superpixels is employed to obtain substitutes for missing details in an up-scaled image. The apparatus (20) comprises a superpixel vector generator (7) configured to generate (10) consistent superpixels for the input image (12) and one or more auxiliary input images (I1, I3) and to generate (11) superpixel test vectors based on the consistent superpixels. A matching block (5) performs a cross-scale self-similarity matching (12) across the input image (12) and the one or more auxiliary input images (I1, I3) using the superpixel test vectors. Finally, an output image generator (22) generates (13) an up-scaled output image (O2) using results of the cross-scale self-similarity matching (12).
摘要翻译：描述了用于放大输入图像（I2）的方法和设备（20），其中使用超级像素的跨尺度自相似性匹配被用来获得放大图像中丢失细节的替代。所述设备（20）包括超像素矢量生成器（7），所述超像素矢量生成器被配置为生成（10）用于输入图像（I 2）和一个或多个辅助输入图像（I 1，I 3）的一致超像素并且基于在一致的超像素上。匹配块（5）使用超像素测试矢量在输入图像（I2）和一个或多个辅助输入图像（I1，I3）上执行跨比例自相似匹配（12）。最后，输出图像生成器（22）使用跨尺度自相似匹配（12）的结果生成（13）放大的输出图像（O2）。

4. 发明授权

EP2862356B1 METHOD AND APPARATUS FOR FUSION OF IMAGES 有权转让
公开(公告)号：EP2862356B1
公开(公告)日：2020-05-06
申请号：EP13726202.8
申请日：2013-05-30
申请人： Thomson Licensing
发明人： SALVADOR MARCOS, Jordi , KOCHALE, Axel , BORSUM, Malte
IPC分类号： H04N13/239

5. 发明公开

EP2979242A1 METHOD AND APPARATUS FOR GENERATING A SUPER-RESOLVED IMAGE FROM A SINGLE IMAGE 有权
标题翻译：方法和设备，用于生成高分辨率图像从单
公开(公告)号：EP2979242A1
公开(公告)日：2016-02-03
申请号：EP14713103.1
申请日：2014-03-26
申请人： Thomson Licensing
发明人： DEAMO, Alberto , SALVADOR MARCOS, Jordi , KOCHALE, Axel
IPC分类号： G06T3/40
CPC分类号： G06T3/4053 , G06K9/6215 , G06K2009/6213 , G06T3/4092 , G06T7/13 , G06T7/73 , G06T2207/20201
摘要： Known methods for generating super-resolved images from single input images have various disadvantages. An improved method for generating a super-resolved image from a single low-resolution input image comprises up-scaling the input image to generate an initial version of the super-resolved image, searching, for each patch of the low-resolution input image, similar low-resolution patches in first search windows within down-sampled versions of the input image, and determining, in less down-sampled versions of the input image, high-resolution patches that correspond to the similar low-resolution patches. The determined high-resolution patches are cropped, a second search window is determined in the initial version of the super-resolved image, and a best-matching position for each cropped high-resolution patch is searched within the second search window. Finally, each cropped high-resolution patch is added to the super-resolved image at its respective best-matching position.
摘要翻译：从单一的输入图像生成超分辨图像的已知方法有许多缺点。用于从单个低分辨率输入图像生成一个超分辨图像的改进的方法包括向上缩放输入图像的超分辨图像的初始版本，以生成，搜索，对于低分辨率输入图像的每个补丁，在输入图像的下采样版本，和矿业确定性内第一个搜索窗口类似的低分辨率的补丁，在输入图像的少降采样版本，高分辨率的补丁也对应于类似的低分辨率补丁。确定性开采高分辨率补丁被裁剪，第二搜索窗口是确定性的开采在超分辨图像的初始版本，以及用于每一个最佳匹配位置裁剪高分辨率补片的第二搜索窗内的搜索。最后，每个裁剪高分辨率补丁在其respectivement最匹配的位置加入到超分辨图像。

6. 发明授权

EP3105736B1 METHOD FOR PERFORMING SUPER-RESOLUTION ON SINGLE IMAGES AND APPARATUS FOR PERFORMING SUPER-RESOLUTION ON SINGLE IMAGES 有权
公开(公告)号：EP3105736B1
公开(公告)日：2019-01-02
申请号：EP15709423.6
申请日：2015-02-13
申请人： Thomson Licensing
发明人： SALVADOR MARCOS, Jordi , PÉREZ PELLITERO, Eduardo , KOCHALE, Axel
IPC分类号： G06T3/40

7. 发明公开

EP3105736A1 METHOD FOR PERFORMING SUPER-RESOLUTION ON SINGLE IMAGES AND APPARATUS FOR PERFORMING SUPER-RESOLUTION ON SINGLE IMAGES 审中-公开
标题翻译：方法实施静态图像上一个非常高的分辨率和实现极高分辨率的静态图像上
公开(公告)号：EP3105736A1
公开(公告)日：2016-12-21
申请号：EP15709423.6
申请日：2015-02-13
申请人： Thomson Licensing
发明人： SALVADOR MARCOS, Jordi , PÉREZ PELLITERO, Eduardo , KOCHALE, Axel
IPC分类号： G06T3/40
CPC分类号： G06T3/4053 , G06K9/52 , G06K9/6215 , G06K2009/4666 , G06T7/0002
摘要： A noise-aware single-image super-resolution (SI-SR) method and apparatus automatically cancels additive noise while adding detail learnt from lower scales of an input image. In contrast to common SI-SR techniques, the input image is not necessarily assumed to be a clean source of examples. Instead, a recent and efficient in-place cross-scale self-similarity prior is exploited for both learning fine detail examples to complement the interpolation-based upscaled image patches and reducing image noise. Experimental results show a promising performance, despite of the relatively simple algorithm. Both objective and subjective evaluations show large quality improvements when upscaling images immersed in noise.
摘要翻译：的噪声感知单图像超分辨率（SR SI）的方法和装置，同时增加细节从输入图像的低尺度了解到自动取消加性噪声。相较于普通SI SR技术，对输入图像未必是假设的例子干净的来源。取而代之的是，最近的和有效的就地跨尺度自相似更早被利用学习这两个细节的例子来补充基于插值放大后的图像修补程序和降低图像噪声。实验结果表明，有前途的性能，尽管相对简单的算法。客观和主观定期评估表明大质量的提高。当按比例放大沉浸在噪音图像。

8. 发明公开

EP2989607A1 METHOD AND DEVICE FOR PERFORMING SUPER-RESOLUTION ON AN INPUT IMAGE 审中-公开
标题翻译：方法和设备超分辨率的对输入图像应用
公开(公告)号：EP2989607A1
公开(公告)日：2016-03-02
申请号：EP14722615.3
申请日：2014-04-25
申请人： Thomson Licensing
发明人： PEREZ PELLITERO, Eduardo , SALVADOR MARCOS, Jordi , KOCHALE, Axel
IPC分类号： G06T3/40
CPC分类号： G06T3/4053 , G06K9/4604 , G06K9/66 , G06T7/60
摘要： A method for performing super-resolution on an input image having low resolution, comprises generating a generic training data set of descriptors extracted from regions of training images, and for each patch of the input image, determining a defined number of nearest neighbor regions, extracting example patches from the nearest neighbor regions and collecting the example patches in an example patch data base, determining a combination of low-resolution example patches that, according to their descriptors, optimally approximate the current patch, and constructing a high-resolution patch, wherein a super-resolved image is obtained.

9. 发明公开

EP2862356A1 METHOD AND APPARATUS FOR FUSION OF IMAGES 有权转让
标题翻译： VERFAHREN UND VORRICHTUNG ZUR FUSION VON BILDERN
公开(公告)号：EP2862356A1
公开(公告)日：2015-04-22
申请号：EP13726202.8
申请日：2013-05-30
申请人： Thomson Licensing
发明人： SALVADOR MARCOS, Jordi , KOCHALE, Axel , BORSUM, Malte
IPC分类号： H04N13/00 , H04N13/02 , H04N5/262 , H04N5/272
摘要： A method and an apparatus (30) for improving a main image (1) by fusing the richer information contained in a secondary image (2) are described. A 3D structure of the secondary image (2) is retrieved (10) and a parallax-corrected version of the secondary image (2) is generated using the 3D structure. The parallax-corrected version of the secondary image (2) is then fused with the main image (1).
摘要翻译：描述了通过融合二次图像（2）中包含的更丰富的信息来改善主图像（1）的方法和装置（30）。检索次要图像（2）的3D结构（10），并且使用3D结构生成二次图像（2）的视差校正版本。然后将二次图像（2）的视差校正版本与主图像（1）融合。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式