-
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：US20180176423A1
公开(公告)日：2018-06-21
申请号：US15380827
申请日：2016-12-15
Applicant: Disney Enterprises, Inc.
Inventor： Jean-Charles Bazin , Alexander Sorkine-Hornung
Abstract: Described herein are apparatus, systems and methods for synchronizing a reference video with an input video. A method comprises extracting first motion data from the input video having a first set of frames, extracting second motion data from the reference video having a second set of frames, computing motion descriptors for each frame in the first set of frames and the second set of frames based on the first and second motion data, respectively, and non-linearly mapping the first set of frames to the second set of frames based on the motion descriptors, respectively.
-
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：US10728427B2
公开(公告)日：2020-07-28
申请号：US15380827
申请日：2016-12-15
Applicant: Disney Enterprises, Inc.
Inventor： Jean-Charles Bazin , Alexander Sorkine-Hornung
Abstract: Described herein are apparatus, systems and methods for synchronizing a reference video with an input video. A method comprises extracting first motion data from the input video having a first set of frames, extracting second motion data from the reference video having a second set of frames, computing motion descriptors for each frame in the first set of frames and the second set of frames based on the first and second motion data, respectively, and non-linearly mapping the first set of frames to the second set of frames based on the motion descriptors, respectively.
-
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.
-
Patent Agency Ranking
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.
-
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：US09412172B2
公开(公告)日：2016-08-09
申请号：US13944437
申请日：2013-07-17
Applicant: DISNEY ENTERPRISES, Inc.
Inventor： Alexander Sorkine-Hornung
CPC classification number: G06T7/0065 , G06T5/00 , G06T7/557 , G06T2200/21 , G06T2207/10052
Abstract: The disclosure provides an approach for generating a sparse representation of a light field. In one configuration, a sparse representation application receives a light field constructed from multiple images, and samples and stores a set of line segments originating at various locations in epipolar-plane images (EPI), until the EPIs are entirely represented and redundancy is eliminated to the extent possible. In addition, the sparse representation application determines and stores difference EPIs that account for variations in the light field. Taken together, the line segments and the difference EPIs compactly store all relevant information that is necessary to reconstruct the full 3D light field and extract an arbitrary input image with a corresponding depth map, or a full 3D point cloud, among other things. This concept also generalizes to higher dimensions. In a 4D light field, for example, the principles of eliminating redundancy and storing a difference volume remain valid.
Abstract translation: 本公开提供了一种用于产生光场的稀疏表示的方法。 在一种配置中，稀疏表示应用程序接收由多个图像构成的光场，并且采样并存储源自于在极性平面图像（EPI）中的不同位置的一组线段，直到EPI被完全表示并且冗余被消除为止 可能的程度。 此外，稀疏表示应用程序确定并存储解释光场中的变化的差分EPI。 总之，线段和差异EPI紧凑地存储重建完整3D光场所需的所有相关信息，并提取具有相应深度图或完整3D点云的任意输入图像等。 这个概念也概括为更高的维度。 例如，在4D光场中，消除冗余和存储差分体积的原理保持有效。
-
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.
-
-
-
-
-
-
-
-
-
Search Results
14
records
(took 0.019 seconds)
