-
公开(公告)号：US11670043B2
公开(公告)日：2023-06-06
申请号：US17314344
申请日：2021-05-07
Applicant: CANON KABUSHIKI KAISHA
Inventor： Keigo Yoneda
CPC classification number: G06T15/60 , G06T7/174 , G06T7/194 , G06T15/205
Abstract: A virtual viewpoint foreground image generating unit generates a virtual viewpoint foreground image, which is an image of a foreground object seen from a virtual viewpoint without a shadow, based on received multi-viewpoint images and a received virtual viewpoint parameter. A virtual viewpoint background image generating unit generates a virtual viewpoint background image, which is an image of a background object seen from the virtual viewpoint, based on the received multi-viewpoint images and virtual viewpoint parameter. A shadow mask image generating unit generates shadow mask images from the received multi-viewpoint images. A shadow-added virtual viewpoint background image generating unit renders a shadow in the virtual viewpoint background image based on the received virtual viewpoint background image, shadow mask images, and virtual viewpoint parameter. A combined image generating unit generates a virtual viewpoint image by combining the virtual viewpoint foreground image with the shadow-added virtual viewpoint background image.
-
公开(公告)号：US20210120224A1
公开(公告)日：2021-04-22
申请号：US17133770
申请日：2020-12-24
Applicant: CANON KABUSHIKI KAISHA
Inventor： Keigo Yoneda
IPC: H04N13/282 , H04N5/222 , H04N5/247 , H04N13/296 , H04N5/783
Abstract: A control is performed such that a speed of change of the virtual viewpoint which is changed in accordance with acceptance of an input according to a specific user operation during playback of the virtual viewpoint image at a first playback speed becomes lower than a speed of change of the virtual viewpoint which is changed in accordance with acceptance of an input according to the specific user operation during playback of the virtual viewpoint image at a second playback speed higher than the first playback speed.
-
公开(公告)号：US11521346B2
公开(公告)日：2022-12-06
申请号：US17382473
申请日：2021-07-22
Applicant: CANON KABUSHIKI KAISHA
Inventor： Keigo Yoneda
IPC: G06T15/20
Abstract: An image processing apparatus obtains virtual viewpoint information indicating at least a position of a virtual viewpoint and a view direction from the virtual viewpoint and generates a virtual viewpoint image based on the virtual viewpoint information and a plurality of images captured from a plurality of viewpoints by hiding processing a specific region of the virtual viewpoint image, the specific region being determined based on that the obtained virtual viewpoint information satisfies a condition.
-
公开(公告)号：US11057609B2
公开(公告)日：2021-07-06
申请号：US16784731
申请日：2020-02-07
Applicant: CANON KABUSHIKI KAISHA
Inventor： Keigo Yoneda , Michio Aizawa
IPC: H04N13/279 , H04N13/282 , G06T19/00
Abstract: An information processing apparatus sets a plurality of key frames that each indicate a position of a virtual viewpoint that corresponds to a virtual viewpoint image, the plurality of key frames corresponding to different times, the virtual viewpoint image being generated based on images of an image capture region captured by a plurality of image capturing apparatuses from different directions. The information processing apparatus determines, based on a position of a virtual viewpoint indicated by a set first key frame and a position of a virtual viewpoint indicated by a set second key frame, a moving path of the virtual viewpoints during a time period between time that corresponds to the first key frame and time that corresponds to the second key frame, and outputs viewpoint information that indicates the determined moving path of the virtual viewpoints.
-
5.发明申请公开(公告)号：US20220189078A1
公开(公告)日：2022-06-16
申请号：US17525251
申请日：2021-11-12
Applicant: CANON KABUSHIKI KAISHA
Inventor： Keigo Yoneda
Abstract: An image processing apparatus obtains one or plurality of images based on capturing by one or plurality of image capturing apparatuses, obtains information related to a virtual object, and generates a two-dimensional image including the virtual object, based on the one or plurality of obtained images and the obtained information related to the virtual object. The image processing apparatus generates the two-dimensional image by determining color information of the virtual object based on color information of a real object included in the one or plurality of images.
-
Patent Agency Ranking
公开(公告)号：US20210358204A1
公开(公告)日：2021-11-18
申请号：US17314344
申请日：2021-05-07
Applicant: CANON KABUSHIKI KAISHA
Inventor： Keigo Yoneda
Abstract: A virtual viewpoint foreground image generating unit generates a virtual viewpoint foreground image, which is an image of a foreground object seen from a virtual viewpoint without a shadow, based on received multi-viewpoint images and a received virtual viewpoint parameter. A virtual viewpoint background image generating unit generates a virtual viewpoint background image, which is an image of a background object seen from the virtual viewpoint, based on the received multi-viewpoint images and virtual viewpoint parameter. A shadow mask image generating unit generates shadow mask images from the received multi-viewpoint images. A shadow-added virtual viewpoint background image generating unit renders a shadow in the virtual viewpoint background image based on the received virtual viewpoint background image, shadow mask images, and virtual viewpoint parameter. A combined image generating unit generates a virtual viewpoint image by combining the virtual viewpoint foreground image with the shadow-added virtual viewpoint background image.
-
7.发明申请公开(公告)号：US20200275083A1
公开(公告)日：2020-08-27
申请号：US16784731
申请日：2020-02-07
Applicant: CANON KABUSHIKI KAISHA
Inventor： Keigo Yoneda , Michio Aizawa
IPC: H04N13/279 , G06T19/00 , H04N13/282
Abstract: An information processing apparatus sets a plurality of key frames that each indicate a position of a virtual viewpoint that corresponds to a virtual viewpoint image, the plurality of key frames corresponding to different times, the virtual viewpoint image being generated based on images of an image capture region captured by a plurality of image capturing apparatuses from different directions. The information processing apparatus determines, based on a position of a virtual viewpoint indicated by a set first key frame and a position of a virtual viewpoint indicated by a set second key frame, a moving path of the virtual viewpoints during a time period between time that corresponds to the first key frame and time that corresponds to the second key frame, and outputs viewpoint information that indicates the determined moving path of the virtual viewpoints.
-
公开(公告)号：US20190221029A1
公开(公告)日：2019-07-18
申请号：US16244688
申请日：2019-01-10
Applicant: CANON KABUSHIKI KAISHA
Inventor： Keigo Yoneda
Abstract: An image processing apparatus that generates a virtual viewpoint image based on images obtained by a plurality of cameras that capture an image capturing area from a plurality of directions and on viewpoint information indicating a position and direction of a virtual viewpoint, the image processing apparatus including: a determining unit configured to determine a priority of an object in the image capturing area; a control unit configured to control a display manner of the object in the virtual viewpoint image, based on the priority of the object determined by the determining unit, so that processing time related to generation of the virtual viewpoint image does not exceed a predetermined amount of time; and a generating unit configured to generate the virtual viewpoint image according to control by the control unit.
-
9.发明授权公开(公告)号：US11941729B2
公开(公告)日：2024-03-26
申请号：US17525251
申请日：2021-11-12
Applicant: CANON KABUSHIKI KAISHA
Inventor： Keigo Yoneda
CPC classification number: G06T11/001 , G06F18/24 , G06T7/50 , G06T7/70 , G06T7/90 , G06T2207/20212 , G06T2207/30244
Abstract: An image processing apparatus obtains one or plurality of images based on capturing by one or plurality of image capturing apparatuses, obtains information related to a virtual object, and generates a two-dimensional image including the virtual object, based on the one or plurality of obtained images and the obtained information related to the virtual object. The image processing apparatus generates the two-dimensional image by determining color information of the virtual object based on color information of a real object included in the one or plurality of images.
-
10.发明申请公开(公告)号：US20220383589A1
公开(公告)日：2022-12-01
申请号：US17819095
申请日：2022-08-11
Applicant: CANON KABUSHIKI KAISHA
Inventor： Shu Fujita , Keigo Yoneda , Shuntaro Aratani , Atsushi Date , Toshiaki Fujii , Keita Takahashi , Takashi Sugie
Abstract: An image generation apparatus obtains a virtual viewpoint image generated based on captured images obtained by image capture of an object by a plurality of image capture devices from a plurality of viewpoints and three-dimensional shape data on the object, and removes noise in the virtual viewpoint image obtained, the noise being generated due to accuracy of the three-dimensional shape data.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.019 seconds)
