-
公开(公告)号：US10122994B2
公开(公告)日：2018-11-06
申请号：US15799831
申请日：2017-10-31
Applicant: Disney Enterprises, Inc.
Inventor： Kaan Yücer , Changil Kim , Alexander Sorkine-Hornung , Olga Sorkine-Hornung
IPC: G06T15/20 , G06T17/20 , G06T7/557 , G06T7/564 , G06T7/593 , H04N13/271 , H04N13/106 , H04N13/15 , G06T15/04
Abstract: The present disclosure relates to techniques for reconstructing an object in three dimensions that is captured in a set of two-dimensional images. The object is reconstructed in three dimensions by computing depth values for edges of the object in the set of two-dimensional images. The set of two-dimensional images may be samples of a light field surrounding the object. The depth values may be computed by exploiting local gradient information in the set of two-dimensional images. After computing the depth values for the edges, depth values between the edges may be determined by identifying types of the edges (e.g., a texture edge, a silhouette edge, or other type of edge). Then, the depth values from the set of two-dimensional images may be aggregated in a three-dimensional space using a voting scheme, allowing the reconstruction of the object in three dimensions.
-
公开(公告)号：US09165401B1
公开(公告)日：2015-10-20
申请号：US14156368
申请日：2014-01-15
Applicant: Disney Enterprises, Inc.
Inventor： Changil Kim , Alexander Sorkine Hornung , Ulrich Mueller , Yael Pritch , Henning Zimmer , Markus Gross
IPC: G06T15/50
CPC classification number: G06T15/50 , H04N13/111 , H04N13/275
Abstract: Methods and systems for generating stereoscopic content with granular control over binocular disparity based on multi-perspective imaging from representations of light fields are provided. A reference image, a three-dimensional (“3D”) representation of a light field corresponding to the reference image, and a goal disparity image that indicates a goal binocular disparity for one or more pixels of the reference image may be received. For each pixel of an output image corresponding to the reference image, a point within the light field that is a closest match for the goal binocular disparity of a corresponding pixel of the goal disparity image may be determined. A stereoscopic image pair including the reference image and the output image may be generated.
Abstract translation: 提供了基于从光场表示的多视角成像产生具有对双目视差的细粒度控制的立体内容的方法和系统。 可以接收参考图像，对应于参考图像的光场的三维（“3D”）表示和指示参考图像的一个或多个像素的目标双目视差的目标视差图像。 对于与参考图像相对应的输出图像的每个像素，可以确定与目标视差图像的对应像素的目标双目视差最接近匹配的光场内的点。 可以生成包括参考图像和输出图像的立体图像对。
-
公开(公告)号：US10887581B2
公开(公告)日：2021-01-05
申请号：US15799663
申请日：2017-10-31
Applicant: Disney Enterprises, Inc.
Inventor： Kaan Yücer , Changil Kim , Alexander Sorkine-Hornung , Olga Sorkine-Hornung
IPC: G06K9/00 , H04N13/271 , H04N13/106 , H04N13/15 , G06T17/20 , H04N13/232 , G06T7/564 , G06T7/557 , G06T7/593 , G06T15/20 , G06T15/04
Abstract: The present disclosure relates to techniques for reconstructing an object in three dimensions that is captured in a set of two-dimensional images. The object is reconstructed in three dimensions by computing depth values for edges of the object in the set of two-dimensional images. The set of two-dimensional images may be samples of a light field surrounding the object. The depth values may be computed by exploiting local gradient information in the set of two-dimensional images. After computing the depth values for the edges, depth values between the edges may be determined by identifying types of the edges (e.g., a texture edge, a silhouette edge, or other type of edge). Then, the depth values from the set of two-dimensional images may be aggregated in a three-dimensional space using a voting scheme, allowing the reconstruction of the object in three dimensions.
-
公开(公告)号：US10319080B2
公开(公告)日：2019-06-11
申请号：US16029328
申请日：2018-07-06
Applicant: Disney Enterprises, Inc.
Inventor： Changil Kim , Olga Sorkine-Hornung , Christopher Schroers , Henning Zimmer , Katja Wolff , Mario Botsch , Alexander Sorkine-Hornung
Abstract: Enhanced removing of noise and outliers from one or more point sets generated by image-based 3D reconstruction techniques is provided. In accordance with the disclosure, input images and corresponding depth maps can be used to remove pixels that are geometrically and/or photometrically inconsistent with the colored surface implied by the input images. This allows standard surface reconstruction methods (such as Poisson surface reconstruction) to perform less smoothing and thus achieve higher quality surfaces with more features. In some implementations, the enhanced point-cloud noise removal in accordance with the disclosure can include computing per-view depth maps, and detecting and removing noisy points and outliers from each per-view point cloud by checking if points are consistent with the surface implied by the other input views.
-
公开(公告)号：US20180137674A1
公开(公告)日：2018-05-17
申请号：US15799831
申请日：2017-10-31
Applicant: Disney Enterprises, Inc.
Inventor： Kaan Yücer , Changil Kim , Alexander Sorkine-Hornung , Olga Sorkine-Hornung
CPC classification number: H04N13/271 , G06T7/557 , G06T7/564 , G06T7/593 , G06T15/04 , G06T15/205 , G06T17/20 , G06T17/205 , G06T2200/21 , G06T2207/10052 , H04N13/106 , H04N13/15 , H04N13/232
Abstract: The present disclosure relates to techniques for reconstructing an object in three dimensions that is captured in a set of two-dimensional images. The object is reconstructed in three dimensions by computing depth values for edges of the object in the set of two-dimensional images. The set of two-dimensional images may be samples of a light field surrounding the object. The depth values may be computed by exploiting local gradient information in the set of two-dimensional images. After computing the depth values for the edges, depth values between the edges may be determined by identifying types of the edges (e.g., a texture edge, a silhouette edge, or other type of edge). Then, the depth values from the set of two-dimensional images may be aggregated in a three-dimensional space using a voting scheme, allowing the reconstruction of the object in three dimensions.
-
Patent Agency Ranking
公开(公告)号：US09786062B2
公开(公告)日：2017-10-10
申请号：US13944337
申请日：2013-07-17
Applicant: DISNEY Enterprises, Inc.
Inventor： Alexander Sorkine-Hornung , Changil Kim , Henning Zimmer , Yael Pritch , Markus Gross
CPC classification number: G06T7/557 , G06T7/50 , G06T7/593 , G06T2207/10016 , G06T2207/10052 , G06T2207/20016
Abstract: The disclosure provides an approach for estimating depth in a scene. According to one aspect, regions where the depth estimation is expected to perform well may first be identified in full-resolution epipolar-plane images (EPIs) generated from a plurality of images of the scene. Depth estimates for EPI-pixels with high edge confidence are determined by testing a number of discrete depth hypotheses and picking depths that lead to highest color density of sampled EPI-pixels. The depth estimate may also be propagated throughout the EPIs. This process of depth estimation and propagation may be iterated until all EPI-pixels with high edge confidence have been processed, and all EPIs may also be processed in this manner. The EPIs are then iteratively downsampled to coarser resolutions, at which edge confidence for EPI-pixels not yet processed are determined, depth estimates of EPI-pixels with high edge confidence made, and depth estimates propagated throughout the EPIs.
-
公开(公告)号：US20180139436A1
公开(公告)日：2018-05-17
申请号：US15799663
申请日：2017-10-31
Applicant: Disney Enterprises, Inc.
Inventor： Kaan Yücer , Changil Kim , Alexander Sorkine-Hornung , Olga Sorkine-Hornung
CPC classification number: H04N13/271 , G06T7/557 , G06T7/564 , G06T7/593 , G06T15/04 , G06T15/205 , G06T17/20 , G06T17/205 , G06T2200/21 , G06T2207/10052 , H04N13/106 , H04N13/15 , H04N13/232
Abstract: The present disclosure relates to techniques for reconstructing an object in three dimensions that is captured in a set of two-dimensional images. The object is reconstructed in three dimensions by computing depth values for edges of the object in the set of two-dimensional images. The set of two-dimensional images may be samples of a light field surrounding the object. The depth values may be computed by exploiting local gradient information in the set of two-dimensional images. After computing the depth values for the edges, depth values between the edges may be determined by identifying types of the edges (e.g., a texture edge, a silhouette edge, or other type of edge). Then, the depth values from the set of two-dimensional images may be aggregated in a three-dimensional space using a voting scheme, allowing the reconstruction of the object in three dimensions.
-
公开(公告)号：US20180096463A1
公开(公告)日：2018-04-05
申请号：US15283121
申请日：2016-09-30
Applicant: Disney Enterprises, Inc.
Inventor： Changil Kim , Olga Sorkine-Hornung , Christopher Schroers , Henning Zimmer , Katja Wolff , Mario Botsch , Alexander Sorkine-Hornung
CPC classification number: G06T5/002 , G06T13/40 , G06T15/06 , G06T17/20 , G06T2207/10024 , G06T2207/10028
Abstract: Enhanced removing of noise and outliers from one or more point sets generated by image-based 3D reconstruction techniques is provided. In accordance with the disclosure, input images and corresponding depth maps can be used to remove pixels that are geometrically and/or photometrically inconsistent with the colored surface implied by the input images. This allows standard surface reconstruction methods (such as Poisson surface reconstruction) to perform less smoothing and thus achieve higher quality surfaces with more features. In some implementations, the enhanced point-cloud noise removal in accordance with the disclosure can include computing per-view depth maps, and detecting and removing noisy points and outliers from each per-view point cloud by checking if points are consistent with the surface implied by the other input views.
-
公开(公告)号：US09843776B2
公开(公告)日：2017-12-12
申请号：US14800288
申请日：2015-07-15
Applicant: DISNEY ENTERPRISES, INC.
Inventor： Changil Kim , Alexander Hornung , Simon Heinzle , Wojciech Matusik , Markus Gross
IPC: H04N7/18 , H04N13/02 , G09G5/00 , G02B27/01 , H04N13/04 , G06T15/06 , G06T15/08 , G06T3/00 , H04N13/00
CPC classification number: H04N7/18 , G02B27/0172 , G02B2027/0134 , G02B2027/0138 , G02B2027/0178 , G06T3/0093 , G06T15/06 , G06T15/08 , G06T2200/04 , G06T2207/10004 , G06T2207/10016 , G06T2210/61 , G06T2219/2008 , G09G5/00 , H04N13/128 , H04N13/239 , H04N13/271 , H04N13/275 , H04N13/282 , H04N13/31 , H04N13/32 , H04N13/339 , H04N13/349 , H04N13/395 , H04N2013/0081 , H04N2013/0092
Abstract: Methods and systems for generating stereoscopic content with granular control over binocular disparity based on multi-perspective imaging from representations of light fields are provided. The stereoscopic content is computed as piecewise continuous cuts through a representation of a light field, minimizing an energy reflecting prescribed parameters such as depth budget, maximum binocular disparity gradient, desired stereoscopic baseline. The methods and systems may be used for efficient and flexible stereoscopic post-processing, such as reducing excessive binocular disparity while preserving perceived depth or retargeting of already captured scenes to various view settings. Moreover, such methods and systems are highly useful for content creation in the context of multi-view autostereoscopic displays and provide a novel conceptual approach to stereoscopic image processing and post-production.
-
公开(公告)号：US10074160B2
公开(公告)日：2018-09-11
申请号：US15283121
申请日：2016-09-30
Applicant: Disney Enterprises, Inc.
Inventor： Changil Kim , Olga Sorkine-Hornung , Christopher Schroers , Henning Zimmer , Katja Wolff , Mario Botsch , Alexander Sorkine-Hornung
CPC classification number: G06T5/002 , G06T13/40 , G06T15/06 , G06T17/00 , G06T17/20 , G06T2207/10024 , G06T2207/10028 , G06T2210/56
Abstract: Enhanced removing of noise and outliers from one or more point sets generated by image-based 3D reconstruction techniques is provided. In accordance with the disclosure, input images and corresponding depth maps can be used to remove pixels that are geometrically and/or photometrically inconsistent with the colored surface implied by the input images. This allows standard surface reconstruction methods (such as Poisson surface reconstruction) to perform less smoothing and thus achieve higher quality surfaces with more features. In some implementations, the enhanced point-cloud noise removal in accordance with the disclosure can include computing per-view depth maps, and detecting and removing noisy points and outliers from each per-view point cloud by checking if points are consistent with the surface implied by the other input views.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.018 seconds)
