公开(公告)号：US20180359474A1

公开(公告)日：2018-12-13

申请号：US16005806

申请日：2018-06-12

Applicant: SONY CORPORATION

Inventor： HIRONARI SAKURAI ,  JUNICHI TANAKA

IPC: H04N19/122 ,  H04N19/625 ,  H04N19/126 ,  H04N19/61 ,  H04N19/129 ,  H04N19/597 ,  H04N19/134 ,  H04N19/30 ,  H04N19/46 ,  H04N19/176

CPC classification number: H04N19/122 ,  H04N19/126 ,  H04N19/129 ,  H04N19/134 ,  H04N19/176 ,  H04N19/30 ,  H04N19/46 ,  H04N19/597 ,  H04N19/61 ,  H04N19/625

Abstract: There is provided an image processing device including a decoding section that decodes an encoded stream and generates quantized transform coefficient data, and an inverse quantization section that, taking transform coefficient data as transform units to be used during inverse orthogonal transform, inversely quantizes the quantized transform coefficient data decoded by the decoding section, such that in a case where a non-square transform unit is selected, the inverse quantization section uses a non-square quantization matrix, corresponding to a non-square transform unit, that is generated from a square quantization matrix corresponding to a square transform unit.

公开(公告)号：US20190238819A1

公开(公告)日：2019-08-01

申请号：US16318431

申请日：2017-07-14

Applicant: SONY CORPORATION

Inventor： KENDAI FURUKAWA ,  JUNICHI TANAKA ,  HIROSHI ORYOJI ,  YUICHI HASEGAWA ,  GOH KOBAYASHI

IPC: H04N13/117 ,  H04N13/282

CPC classification number: H04N13/117 ,  G06T15/205 ,  G06T19/00 ,  H04N13/00 ,  H04N13/282

Abstract: The present disclosure relates to an image processing apparatus and an image processing method that make it possible to generate a texture image of high picture quality at a predetermined viewpoint using an omnidirectional image. A plurality of real cameras image a plurality of reference images at a plurality of viewpoint positions in a plurality of sight line directions. A great weight is applied to a reference image in a sight line direction close to a virtual viewpoint specified in response to a movement of a head mounted display and having a virtual viewpoint position and a sight line direction to generate a virtual viewpoint image by weighted averaging, and the virtual viewpoint image is displayed on the head mounted display. The present disclosure can be applied, for example, to a home server or the like that generates a display image of a predetermined viewpoint from an omnidirectional image.

公开(公告)号：US20200051323A1

公开(公告)日：2020-02-13

申请号：US16338903

申请日：2017-10-05

Applicant: SONY CORPORATION

Inventor： YUICHI ARAKI ,  JUNICHI TANAKA

IPC: G06T15/20

Abstract: The present disclosure relates to an image processing apparatus and an image processing method that enable generation of only a 3D model of a foreground. A reconstruction unit generates a 3D model of the foreground, on the basis of depth images of a plurality of viewpoints and foreground images of the plurality of viewpoints. The present disclosure can be applied to a decoding apparatus or the like that decodes an encoded stream of depth-related images and color images of a 3D model of a plurality of viewpoints, and generates a 3D model of the foreground on the basis of the resultant depth-related images and color images, and virtual viewpoint information including internal parameters and external parameters for virtual cameras of the respective viewpoints, for example.

公开(公告)号：US20190356917A1

公开(公告)日：2019-11-21

申请号：US16524750

申请日：2019-07-29

Applicant: SONY CORPORATION

Inventor： HIRONARI SAKURAI ,  JUNICHI TANAKA

IPC: H04N19/122 ,  H04N19/625 ,  H04N19/126 ,  H04N19/61 ,  H04N19/129 ,  H04N19/597 ,  H04N19/30 ,  H04N19/46 ,  H04N19/176 ,  H04N19/134

Abstract: There is provided an image processing device including a decoding section that decodes an encoded stream and generates quantized transform coefficient data, and an inverse quantization section that, taking transform coefficient data as transform units to be used during inverse orthogonal transform, inversely quantizes the quantized transform coefficient data decoded by the decoding section, such that in a case where a non-square transform unit is selected, the inverse quantization section uses a non-square quantization matrix, corresponding to a non-square transform unit, that is generated from a square quantization matrix corresponding to a square transform unit.

公开(公告)号：US20180077383A1

公开(公告)日：2018-03-15

申请号：US15560202

申请日：2016-02-08

Applicant: SONY CORPORATION

Inventor： MASATO AKAO ,  RYOHEI OKADA ,  JUNICHI TANAKA ,  KAZUHIKO NISHIBORI

IPC: H04N7/14 ,  G06K9/00 ,  G06T11/60 ,  G06T7/73 ,  G06T7/60 ,  G06T7/33

CPC classification number: H04N7/147 ,  G06K9/00228 ,  G06K9/00597 ,  G06T7/337 ,  G06T7/60 ,  G06T7/74 ,  G06T11/60 ,  G06T2207/10016 ,  G06T2207/30201 ,  H04M9/00

Abstract: An information processing apparatus according to the present disclosure includes: a receiver unit that acquires information relevant to a sight line of a user of a communication partner from a communication partner terminal that performs remote communication; a face detection unit that detects information relevant to a position and a size of a face of the user of the communication partner, on the basis of a video signal that includes the face of the user of the communication partner and is received from the communication partner terminal; and a superimposition unit that displays and superimposes a sight line position of the user of the communication partner on the video signal that includes the face of the user of the communication partner, on the basis of the information relevant to the sight line of the user of the communication partner and the information relevant to the position and the size of the face of the user of the communication partner.

公开(公告)号：US20190287289A1

公开(公告)日：2019-09-19

申请号：US16318189

申请日：2017-07-14

Applicant: SONY CORPORATION

Inventor： YUICHI ARAKI ,  JUNICHI TANAKA ,  HIROSHI ORYOJI ,  YUICHI HASEGAWA ,  TOORU MASUDA ,  TETSUYA FUKUYASU

IPC: G06T15/04 ,  G06T15/10 ,  G06T15/08 ,  H04N13/15

Abstract: The present disclosure relates to an image processing apparatus and an image processing method that make it possible to generate a texture image of high picture quality at a predetermined viewpoint using an omnidirectional image.An ML3D model generation section receives transmission information in which auxiliary information is added to at least one of texture information of a first layer, depth information of the first layer, texture information of a second layer or depth information of the second layer, and executes predetermined image processing using the auxiliary information for at least one of the texture information of the first layer, the depth information of the first layer, the texture information of the second layer or the depth information of the second layer. The present disclosure can be applied, for example, to a home server that generates a display image of a predetermined viewpoint from an omnidirectional image or the like.

公开(公告)号：US20170188030A1

公开(公告)日：2017-06-29

申请号：US15406911

申请日：2017-01-16

Applicant: SONY CORPORATION

Inventor： HIRONARI SAKURAI ,  JUNICHI TANAKA

IPC: H04N19/122 ,  H04N19/61 ,  H04N19/126 ,  H04N19/129

CPC classification number: H04N19/122 ,  H04N19/126 ,  H04N19/129 ,  H04N19/134 ,  H04N19/176 ,  H04N19/30 ,  H04N19/46 ,  H04N19/597 ,  H04N19/61 ,  H04N19/625

Abstract: There is provided an image processing device including a decoding section that decodes an encoded stream and generates quantized transform coefficient data, and an inverse quantization section that, taking transform coefficient data as transform units to be used during inverse orthogonal transform, inversely quantizes the quantized transform coefficient data decoded by the decoding section, such that in a case where a non-square transform unit is selected, the inverse quantization section uses a non-square quantization matrix, corresponding to a non-square transform unit, that is generated from a square quantization matrix corresponding to a square transform unit.