-
公开(公告)号：US10832374B2
公开(公告)日：2020-11-10
申请号：US14997448
申请日：2016-01-15
发明人： Henning Zimmer , Olga Sorkine Hornung , Oliver Wang , Alexander Sorkine Hornung , Wenzel Jakob , Fabrice Pierre Armand Rousselle , Wojciech Krzysztof Jarosz , David M. Adler
摘要： Particular embodiments perform a light path analysis of an image comprising a scene, wherein the scene comprises at least one refractive or reflective object. The image may be decomposed based on the light path analysis into a plurality of components, each of the components representing a contribution to lighting in the scene by a different type of light interaction. For each of the components, one or more motion vectors are extracted for each of the components in order to capture motion in the scene. Finally, a final contribution of each of the components to the image is computed based on the motion vectors.
-
2.发明授权公开(公告)号：US09900505B2
公开(公告)日：2018-02-20
申请号：US14339253
申请日：2014-07-23
发明人： Federico Perazzi , Alexander Sorkine Hornung , Henning Zimmer , Oliver Wang , Peter Kaufmann , Scott Watson
CPC分类号： H04N5/23238 , G06T3/4038 , H04N5/2258 , H04N5/247 , H04N5/2628 , H04N5/265
摘要： Systems and methods for generating a panoramic video from unstructured camera arrays. The systems and methods are configured to statically align corresponding image-frames of respective input video streams, warp the aligned image-frames according to a warping-order, and relax the warped image-frames thereby generating a temporally coherent panoramic video. Methods according to embodiments this invention utilize a new parallax-warping-error metric that is devised to capture structural differences created by parallax artifacts. The parallax-warping-error metric is effective in finding an optimal warping-order and in driving the warping process, resulting in a panoramic video with minimal parallax artifacts.
-
公开(公告)号：US20170345151A1
公开(公告)日：2017-11-30
申请号：US15165056
申请日：2016-05-26
CPC分类号： G06T7/10 , G06T2207/10016 , G06T2207/20092 , G06T2207/20112 , G11B27/28 , G11B27/3081 , G11B27/34
摘要： This disclosure relates to system and methods for segmenting a video in a higher order dimensional space. A video may be segmented by obtaining visual information defining an image of the video. The visual information may include pixels of the image and may be represented in a display space having a first dimensionality. A designation of a subset of the visual information represented in the display space as a part of an object portrayed in the image may be obtained. The visual information and the designation may be represented in the higher order dimensional space having a second dimensionality greater than the first dimensionality. An association of the visual information represented in the higher order dimensional space with the object may be obtained. The association may be correlated with the visual information represented in the display space. The correlation may define a location of the object in the image.
-
公开(公告)号：US09571786B1
公开(公告)日：2017-02-14
申请号：US14884046
申请日：2015-10-15
CPC分类号： H04N7/0135 , G06T3/4084 , H04N5/783 , H04N7/0132
摘要： Interpolating frames of a video may provide a technique for one or more of frame rate conversion, temporal upsampling for generating slow motion video, image morphing, virtual view synthesis, and/or other video applications. A system may be configured to interpolated frames of a video by leveraging frequency domain representations of individual frames. The frequency domain representations may be decomposed into set of discrete functions that make up the frequency domain representations. Corresponding functions from sets of functions associated with frames with which an interpolated frame is to be determined may be identified. Phase differences between corresponding functions may be determined. Interpolated functions between the corresponding functions may be determined based on the determined phased differences. Information describing spatial domain representations of interpolated frames may be determined based on the interpolated functions.
摘要翻译： 视频的插值帧可以提供用于帧速率转换，用于产生慢动作视频的时间上采样，图像变形，虚拟视图合成和/或其他视频应用中的一个或多个的技术。 系统可以被配置为通过利用各个帧的频域表示来内插视频的帧。 频域表示可以被分解为组成频域表示的离散函数集合。 可以识别与要被确定内插帧的帧相关联的函数集的相应函数。 可以确定相应功能之间的相位差。 可以基于确定的相位差来确定相应功能之间的内插函数。 可以基于内插函数来确定描述插值帧的空间域表示的信息。
-
5.发明申请Panoramic Video from Unstructured Camera Arrays with Globally Consistent Parallax Removal 有权具有全局一致性视差去除的非结构化摄像机阵列的全景视频公开(公告)号：US20160028950A1
公开(公告)日：2016-01-28
申请号：US14339253
申请日：2014-07-23
发明人： Federico PERAZZI , Alexander Sorkine Hornung , Henning Zimmer , Oliver Wang , Peter Kaufmann , Scott Watson
CPC分类号： H04N5/23238 , G06T3/4038 , H04N5/2258 , H04N5/247 , H04N5/2628 , H04N5/265
摘要： Systems and methods for generating a panoramic video from unstructured camera arrays. The systems and methods are configured to statically align corresponding image-frames of respective input video streams, warp the aligned image-frames according to a warping-order, and relax the warped image-frames thereby generating a temporally coherent panoramic video. Methods according to embodiments this invention utilize a new parallax-warping-error metric that is devised to capture structural differences created by parallax artifacts. The parallax-warping-error metric is effective in finding an optimal warping-order and in driving the warping process, resulting in a panoramic video with minimal parallax artifacts.
摘要翻译： 用于从非结构化摄像机阵列生成全景视频的系统和方法。 这些系统和方法被配置为静态对齐各个输入视频流的相应图像帧，根据翘曲顺序扭转对齐的图像帧，并且松弛扭曲的图像帧，从而产生时间上一致的全景视频。 根据本发明的实施例的方法利用新的视差扭曲误差度量来设计以捕获由视差伪影产生的结构差异。 视差扭曲误差度量在找到最佳翘曲顺序和驱动翘曲过程中是有效的，导致具有最小视差伪像的全景视频。
-
6.发明授权公开(公告)号：US09648303B1
公开(公告)日：2017-05-09
申请号：US14970346
申请日：2015-12-15
CPC分类号： H04N13/264 , G06K9/00664 , G06T7/246 , G06T7/73 , G06T2207/10021 , G06T2207/30244
摘要： Scenes reconstruction may be performed using videos that capture the scenes at high resolution and frame rate. Scene reconstruction may be associated with determining camera orientation and/or location (“camera pose”) throughout the video, three-dimensional coordinates of feature points detected in frames of the video, and/or other information. Individual videos may have multiple frames. Feature points may be detected in, and tracked over, the frames. Estimations of camera pose may be made for individual subsets of frames. One or more estimations of camera pose may be determined as fixed estimations. The estimated camera poses for the frames included in the subsets of frames may be updated based on the fixed estimations. Camera pose for frames not included in the subsets of frames may be determined to provide globally consistent camera poses and three-dimensional coordinates for feature points of the video.
-
公开(公告)号：US10832375B2
公开(公告)日：2020-11-10
申请号：US14997453
申请日：2016-01-15
发明人： Henning Zimmer , Olga Sorkine Hornung , Oliver Wang , Alexander Sorkine Hornung , Wenzel Jakob , Fabrice Pierre Armand Rousselle , Wojciech Krzysztof Jarosz , David M. Adler
摘要： Particular embodiments decompose an image comprising a scene into a diffuse component and a specular component. Each of the components represent a contribution to lighting in the scene. A set of motion vectors may be extracted in order to capture motion in the scene. Finally, a final contribution of each of the components to the image may be computed based on the motion vectors.
-
公开(公告)号：US09911194B2
公开(公告)日：2018-03-06
申请号：US15165056
申请日：2016-05-26
CPC分类号： G06T7/10 , G06T2207/10016 , G06T2207/20092 , G06T2207/20112 , G11B27/28 , G11B27/3081 , G11B27/34
摘要： This disclosure relates to system and methods for segmenting a video in a higher order dimensional space. A video may be segmented by obtaining visual information defining an image of the video. The visual information may include pixels of the image and may be represented in a display space having a first dimensionality. A designation of a subset of the visual information represented in the display space as a part of an object portrayed in the image may be obtained. The visual information and the designation may be represented in the higher order dimensional space having a second dimensionality greater than the first dimensionality. An association of the visual information represented in the higher order dimensional space with the object may be obtained. The association may be correlated with the visual information represented in the display space. The correlation may define a location of the object in the image.
-
公开(公告)号：US20160210778A1
公开(公告)日：2016-07-21
申请号：US14997453
申请日：2016-01-15
发明人： Henning Zimmer , Olga Sorkine-Hornung , Oliver Wang , Alexander Sorkine-Hornung , Wenzel Jakob , Fabrice Pierre Armand Rousselle , Wojciech Krzysztof Jarosz , David M. Adler
CPC分类号： G06T3/4007 , G06T5/002 , G06T15/506
摘要： Particular embodiments decompose an image comprising a scene into a diffuse component and a specular component. Each of the components represent a contribution to lighting in the scene. A set of motion vectors may be extracted in order to capture motion in the scene. Finally, a final contribution of each of the components to the image may be computed based on the motion vectors.
摘要翻译： 特定实施例将包括场景的图像分解成漫射分量和镜面分量。 每个组件都代表对现场照明的贡献。 可以提取一组运动矢量以捕获场景中的运动。 最后，可以基于运动矢量来计算每个分量对图像的最终贡献。
-
公开(公告)号：US20160210777A1
公开(公告)日：2016-07-21
申请号：US14997448
申请日：2016-01-15
发明人： Henning Zimmer , Olga Sorkine-Hornung , Oliver Wang , Alexander Sorkine-Hornung , Wenzel Jakob , Fabrice Pierre Armand Rousselle , Wojciech Krzysztof Jarosz , David M. Adler
CPC分类号： G06T3/4007 , G06T5/002 , G06T15/506
摘要： Particular embodiments perform a light path analysis of an image comprising a scene, wherein the scene comprises at least one refractive or reflective object. The image may be decomposed based on the light path analysis into a plurality of components, each of the components representing a contribution to lighting in the scene by a different type of light interaction. For each of the components, one or more motion vectors are extracted for each of the components in order to capture motion in the scene. Finally, a final contribution of each of the components to the image is computed based on the motion vectors.
摘要翻译： 特定实施例对包括场景的图像进行光路分析，其中场景包括至少一个折射或反射物体。 图像可以基于光路分析分解为多个分量，每个分量通过不同类型的光交互表示对场景中的照明的贡献。 对于每个组件，为每个组件提取一个或多个运动矢量，以捕获场景中的运动。 最后，基于运动矢量计算每个分量对图像的最终贡献。
-
-
-
-
-
-
-
-
-
搜索结果
29 条记录 (耗时 0.018 秒)
