公开(公告)号：US20210099711A1

公开(公告)日：2021-04-01

申请号：US17031782

申请日：2020-09-24

Applicant: Apple Inc.

Inventor： Alexandros Tourapis ,  Jungsun Kim ,  Khaled Mammou ,  Liviu Traian Christian Tulvan ,  Marius Preda

IPC: H04N19/139 ,  H04N19/107 ,  H04N19/147 ,  G06T9/00 ,  H04N19/96

Abstract: A system comprises an encoder configured to compress attribute information for a dynamic point cloud and/or a decoder configured to decompress compressed attribute information for a dynamic point cloud. The dynamic point cloud may include multiple versions of the point cloud at multiple moments in time Attribute values for the point cloud may be compressed at a reference frame using an intra-prediction process and may be compressed at one or more reference frames using an inter-prediction process that takes advantage of temporal relationships between different frames (e.g. versions) of the dynamic point cloud at the different moments in time.

公开(公告)号：US11562507B2

公开(公告)日：2023-01-24

申请号：US17031787

申请日：2020-09-24

Applicant: Apple Inc.

Inventor： Jungsun Kim ,  Alexandros Tourapis ,  Khaled Mammou ,  Chao Cao ,  Marius Preda

IPC: G06V30/00 ,  G06T9/00 ,  G06T5/00 ,  G06T7/73 ,  H04N19/137 ,  H04N19/80 ,  H04N19/172 ,  H04N19/60

Abstract: A system comprises an encoder configured to compress attribute and/or spatial information for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. To compress the attribute and/or spatial information, the encoder is configured to convert a point cloud into an image based representation. Also, the decoder is configured to generate a decompressed point cloud based on an image based representation of a point cloud. In some embodiments, an encoder generates time-consistent patches for multiple version of the point cloud at multiple moments in time and uses the time-consistent patches to generate image based representations of the point cloud at the multiple moments in time.

公开(公告)号：US11202078B2

公开(公告)日：2021-12-14

申请号：US17031782

申请日：2020-09-24

Applicant: Apple Inc.

Inventor： Alexandros Tourapis ,  Jungsun Kim ,  Khaled Mammou ,  Liviu Traian Christian Tulvan ,  Marius Preda

IPC: H04N19/139 ,  H04N19/107 ,  G06T9/00 ,  H04N19/96 ,  H04N19/147 ,  H04N19/172

Abstract: A system comprises an encoder configured to compress attribute information for a dynamic point cloud and/or a decoder configured to decompress compressed attribute information for a dynamic point cloud. The dynamic point cloud may include multiple versions of the point cloud at multiple moments in time Attribute values for the point cloud may be compressed at a reference frame using an intra-prediction process and may be compressed at one or more reference frames using an inter-prediction process that takes advantage of temporal relationships between different frames (e.g. versions) of the dynamic point cloud at the different moments in time.

公开(公告)号：US20210097723A1

公开(公告)日：2021-04-01

申请号：US17031787

申请日：2020-09-24

Applicant: Apple Inc.

Inventor： Jungsun Kim ,  Alexandros Tourapis ,  Khaled Mammou ,  Chao Cao ,  Marius Preda

IPC: G06T9/00 ,  G06T5/00 ,  G06T7/73 ,  H04N19/137 ,  H04N19/60 ,  H04N19/80 ,  H04N19/172

Abstract: A system comprises an encoder configured to compress attribute and/or spatial information for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. To compress the attribute and/or spatial information, the encoder is configured to convert a point cloud into an image based representation. Also, the decoder is configured to generate a decompressed point cloud based on an image based representation of a point cloud. In some embodiments, an encoder generates time-consistent patches for multiple version of the point cloud at multiple moments in time and uses the time-consistent patches to generate image based representations of the point cloud at the multiple moments in time.