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. 发明申请

WO2015006894A1 FEATURE-BASED IMAGE SET COMPRESSION 审中-公开
标题翻译：基于特征的图像集压缩
公开(公告)号：WO2015006894A1
公开(公告)日：2015-01-22
申请号：PCT/CN2013/079352
申请日：2013-07-15
申请人： MICROSOFT CORPORATION , SUN, Xiaoyan , WU, Feng , SHI, Zhongbo
发明人： SUN, Xiaoyan , WU, Feng , SHI, Zhongbo
IPC分类号： H04N5/917
CPC分类号： H04N19/426 , G06K9/52 , G06K9/6218 , H04N5/765 , H04N5/91 , H04N9/8045 , H04N19/136 , H04N19/503 , H04N19/51 , H04N19/65 , H04N19/94
摘要： Some examples may generate one or more sets of compressed images from an image collection. Images from the image collection may be clustered into one or more sets of images based on one or more features in each image. A correlation structure, such as a minimum spanning tree of images, may be created from each of the one or more sets of images based on the one or more features in each image. Feature-based prediction may be performed using the feature-based minimum spanning tree. One or more sets of compressed images corresponding to the one or more sets of images may be generated.
摘要翻译：一些示例可以从图像集合生成一组或多组压缩图像。来自图像集合的图像可以基于每个图像中的一个或多个特征聚类成一组或多组图像。基于每个图像中的一个或多个特征，可以从一个或多个图像组中的每一个创建相关结构，诸如图像的最小生成树。可以使用基于特征的最小生成树来执行基于特征的预测。可以生成对应于一组或多组图像的一组或多组压缩图像。

2. 发明申请

WO2015176280A1 RE-ENCODING IMAGE SETS USING FREQUENCY-DOMAIN DIFFERENCES 审中-公开
标题翻译：使用频域差异重新编码图像集
公开(公告)号：WO2015176280A1
公开(公告)日：2015-11-26
申请号：PCT/CN2014/078136
申请日：2014-05-22
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC , SUN, Xiaoyan , WU, Feng , WU, Hao
发明人： SUN, Xiaoyan , WU, Feng , WU, Hao
IPC分类号： H04N19/40
CPC分类号： H04N19/40 , H04N19/105 , H04N19/124 , H04N19/15 , H04N19/176 , H04N19/44 , H04N19/463 , H04N19/48 , H04N19/50 , H04N19/593 , H04N19/61 , H04N19/619 , H04N19/91
摘要： Approaches to re-encoding image sets using frequency-domain differences, along with corresponding approaches to reversing the re-encoding of the image sets. For example, are- encoding tool computes frequency-domain differences between (a) quantized coefficients for a block from encoded data in a first format and (b) quantized coefficients for a prediction of the block. The re-encoding tool entropy codes the frequency-domain differences, producing encoded data in a second format for the compressed images. Such re-encoding can significantly reduce storage cost for previously compressed images,compared to the storage cost for the previously compressed images in the first format, without hurting image quality. Subsequently, the previously compressed images in the first format can be recovered from the encoded data in the second format. Or, the encoded data in the second format can be decoded to reconstruct the images.
摘要翻译：使用频域差异重新编码图像集的方法，以及反转图像集的重新编码的相应方法。例如，编码工具计算（a）来自第一格式的编码数据的块的量化系数和（b）用于块的预测的量化系数之间的频域差。重新编码工具熵对频域差异进行编码，产生用于压缩图像的第二格式的编码数据。与先前压缩的图像的第一格式的存储成本相比，这种重新编码可以显着降低先前压缩图像的存储成本，而不会损害图像质量。随后，可以从第二格式的编码数据恢复先前压缩的第一格式的图像。或者，可以对第二格式的编码数据进行解码以重构图像。

3. 发明申请

WO2009033119A1 LEARNING-BASED IMAGE COMPRESSION 审中-公开
标题翻译：基于学习的图像压缩
公开(公告)号：WO2009033119A1
公开(公告)日：2009-03-12
申请号：PCT/US2008/075522
申请日：2008-09-06
申请人： MICROSOFT CORPORATION
发明人： SUN, Xiaoyan , WU, Feng , LI, Shipeng
IPC分类号： G06T9/00
CPC分类号： H04N19/59 , H04N19/132 , H04N19/14 , H04N19/587 , H04N19/85 , H04N19/90
摘要： Learning-based image compression is described. In one implementation, an encoder possessing a first set of learned visual knowledge primitives excludes visual information from an image prior to compression. A decoder possessing an independently learned set of visual knowledge primitives synthesizes the excluded visual information into the image after decompression. The encoder and decoder are decoupled with respect to the information excluded at the encoder and the information synthesized at the decoder. This results in superior data compression since the information excluded at the encoder is dropped completely and not transferred to the decoder. Primitive visual elements synthesized at the decoder may be different than primitive visual elements dropped at the encoder, but the resulting reconstituted image is perceptually equivalent to the original image.
摘要翻译：描述基于学习的图像压缩。在一个实现中，具有第一组学习视觉知识原语的编码器在压缩之前从图像中排除视觉信息。具有独立学习的视觉知识图元组的解码器在解压缩之后将排除的视觉信息合成到图像中。编码器和解码器相对于在编码器处排除的信息和在解码器处合成的信息去耦合。这导致优异的数据压缩，因为在编码器处排除的信息完全丢弃并且不传送到解码器。在解码器处合成的原始视觉元素可能不同于在编码器处丢弃的原始视觉元素，但是所产生的重构图像在听觉上等同于原始图像。

4. 发明申请

WO2007124084A1 VISION-BASED COMPRESSION 审中-公开
标题翻译：基于视觉的压缩
公开(公告)号：WO2007124084A1
公开(公告)日：2007-11-01
申请号：PCT/US2007/009702
申请日：2007-04-19
申请人： MICROSOFT CORPORATION
发明人： SUN, Xiaoyan , WU, Feng , LI, Shipeng , LIU, Dong
IPC分类号： H04N7/24
CPC分类号： H04N19/12 , G06T7/12 , H04N19/17 , H04N19/61
摘要： Systems and methods provide vision-based image compression. In one implementation, inpainting is the vision-based technique selected to augment a conventional signal-processing-based technique. For some regions of a source image, an exemplary system efficiently extracts and organizes structural edge information instead of compressing the regions. In one implementation, the system applies binary curve fitting to capture the edge information. A structure-aware inpainter in the decoder can then restore the regions via the edge information, which occupies very little data space or minimal bandwidth in a bitstream that is transmitted from encoder to decoder. Key visual components of the image can still be conventionally compressed. Extracting edge information for some regions instead of compressing them considerably increases overall image compression.
摘要翻译：系统和方法提供基于视觉的图像压缩。在一个实现中，修复是基于视觉的技术，其被选择用于增加常规的基于信号处理的技术。对于源图像的一些区域，示例性系统有效地提取并组织结构边缘信息而不是压缩区域。在一个实现中，系统应用二进制曲线拟合来捕获边缘信息。然后，解码器中的结构感知输入器可以经由边缘信息来恢复区域，该边缘信息在从编码器传送到解码器的比特流中占据非常小的数据空间或最小带宽。图像的主要视觉部件仍然可以被传统地压缩。为某些区域提取边缘信息而不是压缩边缘信息显着增加了整体图像压缩。

5. 发明申请

WO2009002885A3 VIDEO CODING USING SPATIO-TEMPORAL TEXTURE SYNTHESIS 审中-公开
标题翻译：视频编码采用时空纹理综合
公开(公告)号：WO2009002885A3
公开(公告)日：2008-12-31
申请号：PCT/US2008/067803
申请日：2008-06-21
申请人： MICROSOFT CORPORATION
发明人： SUN, Xiaoyan , ZHU, Chunbo , WU, Feng , LI, Shipeng
IPC分类号： H04N7/24
摘要： Systems and methods for video coding using spatio-temporal texture synthesis are described. In one aspect, a video data coding pipeline portion of the codec removes texture blocks from the video data to generate coded video data. The removed texture blocks are selected based on an objective determination that each of the remove texture blocks can be synthesized from spatio-temporal neighboring samples during decoding operations. The objective determinations are made using local block-based motion information independent of global motion models. An indication of which texture blocks were removed is provided to a decoder in addition to the coded video data. Decoding logic of the codec decodes the video data using a standard decoding algorithm. The decoding logic also restores the removed texture blocks via spatio-temporal texture synthesis to generate synthesized video data. The decoded and synthesized video data is presented to a user.
摘要翻译：描述了使用时空纹理合成的视频编码的系统和方法。在一个方面中，编解码器的视频数据译码流水线部分从视频数据移除纹理块以产生经译码视频数据。基于在解码操作期间可以从时空相邻样本合成每个移除纹理块的客观确定来选择移除的纹理块。目标确定是使用与全局运动模型无关的局部基于块的运动信息进行的。除了编码的视频数据之外，还向解码器提供去除了哪些纹理块的指示。编解码器的解码逻辑使用标准解码算法解码视频数据。解码逻辑还通过时空纹理合成来恢复所移除的纹理块以生成合成的视频数据。解码和合成的视频数据呈现给用户。

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