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

US08994722B2 Method for enhancing depth images of scenes using trellis structures 有权
标题翻译：使用网格结构增强场景深度图像的方法
公开(公告)号：US08994722B2
公开(公告)日：2015-03-31
申请号：US13406139
申请日：2012-02-27
申请人： Dong Tian , Yongzhe Wang , Anthony Vetro
发明人： Dong Tian , Yongzhe Wang , Anthony Vetro
IPC分类号： G06T15/20
CPC分类号： G06T15/205
摘要： An image for a virtual view of a scene is generated based on a set of texture images and a corresponding set of depth images acquired of the scene. A set of candidate depths associated with each pixel of a selected image is determined. For each candidate depth, a cost that estimates a synthesis quality of the virtual image is determined. The candidate depth with a least cost is selected to produce an optimal depth for the pixel. Then, the virtual image is synthesized based on the optimal depth of each pixel and the texture images. The method also applies first and second depth enhancement before, and during view synthesis to correct errors or suppress noise due to the estimation or acquisition of the dense depth images and sparse depth features.
摘要翻译：基于一组纹理图像和从该场景获取的对应的一组深度图像来生成用于场景的虚拟视图的图像。确定与所选图像的每个像素相关联的一组候选深度。对于每个候选深度，确定估计虚拟图像的合成质量的成本。选择具有最低成本的候选深度以产生像素的最佳深度。然后，基于每个像素的最佳深度和纹理图像合成虚拟图像。该方法还在视图合成之前和视图合成期间都应用第一和第二深度增强，以校正误差或抑制由于估计或获取密集深度图像和稀疏深度特征而导致的噪声。

2. 发明申请

US20110194024A1 CONTENT ADAPTIVE AND ART DIRECTABLE SCALABLE VIDEO CODING 有权
标题翻译：内容自适应和艺术直观可扩展视频编码
公开(公告)号：US20110194024A1
公开(公告)日：2011-08-11
申请号：US12702195
申请日：2010-02-08
申请人： Nikolce STEFANOSKI , Aljosa SMOLIC , Yongzhe WANG , Manuel LANG , Alexander HORNUNG , Markus GROSS
发明人： Nikolce STEFANOSKI , Aljosa SMOLIC , Yongzhe WANG , Manuel LANG , Alexander HORNUNG , Markus GROSS
IPC分类号： H04N7/01
CPC分类号： H04N19/537 , H04N19/33 , H04N19/463
摘要： Systems, methods and articles of manufacture are disclosed for performing scalable video coding. In one embodiment, non-linear functions are used to predict source video data using retargeted video data. Differences may be determined between the predicted video data and the source video data. The retargeted video data, the non-linear functions, and the differences may be jointly encoded into a scalable bitstream. The scalable bitstream may be transmitted and selectively decoded to produce output video for one of a plurality of predefined target platforms.
摘要翻译：公开了用于执行可缩放视频编码的系统，方法和制品。在一个实施例中，使用非线性函数来使用重定向视频数据来预测源视频数据。可以在预测的视频数据和源视频数据之间确定差异。重定向视频数据，非线性函数和差异可以被联合编码为可分级比特流。可扩展的比特流可以被传输并选择性地解码以产生多个预定目标平台之一的输出视频。

3. 发明申请

US20120206451A1 Method for Enhancing Depth Images of Scenes Using Trellis Structures 有权
标题翻译：使用网格结构增强场景深度图像的方法
公开(公告)号：US20120206451A1
公开(公告)日：2012-08-16
申请号：US13406139
申请日：2012-02-27
申请人： Dong Tian , Yongzhe Wang , Anthony Vetro
发明人： Dong Tian , Yongzhe Wang , Anthony Vetro
IPC分类号： G06T17/30
CPC分类号： G06T15/205
摘要： An image for a virtual view of a scene is generated based on a set of texture images and a corresponding set of depth images acquired of the scene. A set of candidate depths associated with each pixel of a selected image is determined. For each candidate depth, a cost that estimates a synthesis quality of the virtual image is determined. The candidate depth with a least cost is selected to produce an optimal depth for the pixel. Then, the virtual image is synthesized based on the optimal depth of each pixel and the texture images. The method also applies first and second depth enhancement before, and during view synthesis to correct errors or suppress noise due to the estimation or acquisition of the dense depth images and sparse depth features.
摘要翻译：基于一组纹理图像和从该场景获取的对应的一组深度图像来生成用于场景的虚拟视图的图像。确定与所选图像的每个像素相关联的一组候选深度。对于每个候选深度，确定估计虚拟图像的合成质量的成本。选择具有最低成本的候选深度以产生像素的最佳深度。然后，基于每个像素的最佳深度和纹理图像合成虚拟图像。该方法还在视图合成之前和视图合成期间都应用第一和第二深度增强，以校正误差或抑制由于估计或获取密集深度图像和稀疏深度特征而导致的噪声。

4. 发明申请

US20120206442A1 Method for Generating Virtual Images of Scenes Using Trellis Structures 审中-公开
公开(公告)号：US20120206442A1
公开(公告)日：2012-08-16
申请号：US13307936
申请日：2011-11-30
申请人： Dong Tian , Yongzhe Wang , Anthony Vetro
发明人： Dong Tian , Yongzhe Wang , Anthony Vetro
IPC分类号： G06T15/00
CPC分类号： G06T15/205 , G06T15/503 , H04N13/111
摘要： An image for a virtual view of a scene is generated based on a set of texture images and a corresponding set of depth images acquired of the scene. A set of candidate depth values associated with each pixel of a selected image is determined. For each candidate depth value, a cost that estimates a synthesis quality of the virtual image is determined. The candidate depth value with a least cost is selected to produce an optimal depth value for the pixel. Then, the virtual image is synthesized based on the optimal depth value of each pixel and the texture images.

5. 发明授权

US08514932B2 Content adaptive and art directable scalable video coding 有权
标题翻译：内容自适应和艺术可定制的可扩展视频编码
公开(公告)号：US08514932B2
公开(公告)日：2013-08-20
申请号：US12702195
申请日：2010-02-08
申请人： Nikolce Stefanoski , Aljosa Smolic , Yongzhe Wang , Manuel Lang , Alexander Hornung , Markus Gross
发明人： Nikolce Stefanoski , Aljosa Smolic , Yongzhe Wang , Manuel Lang , Alexander Hornung , Markus Gross
IPC分类号： H04N7/12 , H04N7/01 , H04N7/32 , H04N11/02
CPC分类号： H04N19/537 , H04N19/33 , H04N19/463
摘要： Systems, methods and articles of manufacture are disclosed for performing scalable video coding. In one embodiment, non-linear functions are used to predict source video data using retargeted video data. Differences may be determined between the predicted video data and the source video data. The retargeted video data, the non-linear functions, and the differences may be jointly encoded into a scalable bitstream. The scalable bitstream may be transmitted and selectively decoded to produce output video for one of a plurality of predefined target platforms.
摘要翻译：公开了用于执行可缩放视频编码的系统，方法和制品。在一个实施例中，使用非线性函数来使用重定向视频数据来预测源视频数据。可以在预测的视频数据和源视频数据之间确定差异。重定向视频数据，非线性函数和差异可以被联合编码为可分级比特流。可扩展的比特流可以被传输并选择性地解码以产生多个预定目标平台之一的输出视频。

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