Provided are a point cloud data encapsulation method and a point cloud data transmission method. The point cloud data encapsulation method includes: compressing a point cloud media file; and encapsulating the compressed point cloud media file and setting a classification record according to a data type, where the classification record is used for indicating a data type of each portion of point cloud data in the point cloud media file. The problem of low transmission efficiency of the media content and waste of storage space in the point cloud data transmission is solved, the flexibility of the media content combination is increased, management control of a multimedia service is increased, users are given more rights to independently select and acquire the media content, diversified application scenarios are provided, and better multimedia content provision and transmission solutions are provided for network operators.

This application provides a method for predicting a point cloud attribute, an encoder, a decoder, and a storage medium. During point cloud attribute prediction, different selection policies for target adjacent points are designed according to the distribution of repetition points, to determine at least one target adjacent point of a target point, and attribute prediction is performed on the target point according to reconstructed attribute information of the at least one target adjacent point, thereby improving the efficiency and accuracy of point cloud attribute prediction.

This application provides a method for predicting a point cloud attribute, an encoder, a decoder, and a storage medium. During point cloud attribute prediction, different selection policies for target adjacent points are designed according to the distribution of repetition points, to determine at least one target adjacent point of a target point, and attribute prediction is performed on the target point according to reconstructed attribute information of the at least one target adjacent point, thereby improving the efficiency and accuracy of point cloud attribute prediction.

A point cloud data encoding method and decoding method, a device, a medium, and a program product are provided, and relate to the field of point cloud application technologies. One method includes obtaining point cloud data, the point cloud data comprising at least two data points; and sequentially encoding data points in the point cloud data according to encoding orders of the data points, to obtain encoded point cloud data corresponding to the point cloud data, wherein the encoding orders of the data points being determined based on distances among the data points. Another method includes obtaining encoded point cloud data, obtaining reference information, the reference information being used for indicating a start reference data point of an encoding queue; and sequentially decoding, based on the reference information and the encoded point cloud data, data points according to the encoding orders of the data points.

Embodiments of the present disclosure discloses a scene-aware video encoder system. The scene-aware encoder system transforms a sequence of video frames of a video of a scene into a spatio-temporal scene graph. The spatio-temporal scene graph includes nodes representing one or multiple static and dynamic objects in the scene. Each node of the spatio-temporal scene graph describes an appearance, a location, and/or a motion of each of the objects (static and dynamic objects) at different time instances. The nodes of the spatio-temporal scene graph are embedded into a latent space using a spatio-temporal transformer encoding different combinations of different nodes of the spatio-temporal scene graph corresponding to different spatio-temporal volumes of the scene. Each node of the different nodes encoded in each of the combinations is weighted with an attention score determined as a function of similarities of spatio-temporal locations of the different nodes in the combination.

Embodiments of the present disclosure discloses a scene-aware video encoder system. The scene-aware encoder system transforms a sequence of video frames of a video of a scene into a spatio-temporal scene graph. The spatio-temporal scene graph includes nodes representing one or multiple static and dynamic objects in the scene. Each node of the spatio-temporal scene graph describes an appearance, a location, and/or a motion of each of the objects (static and dynamic objects) at different time instances. The nodes of the spatio-temporal scene graph are embedded into a latent space using a spatio-temporal transformer encoding different combinations of different nodes of the spatio-temporal scene graph corresponding to different spatio-temporal volumes of the scene. Each node of the different nodes encoded in each of the combinations is weighted with an attention score determined as a function of similarities of spatio-temporal locations of the different nodes in the combination.

Various concepts which further improve multi-view/layer coding concepts, are described.

Various concepts which further improve multi-view/layer coding concepts, are described.

A method, apparatus and computer program product are provided to signal and store compressed point clouds in video encoding. The method, apparatus and computer program product may be utilized in conjunction with a variety of video formats. Relative to encoding of compressed point clouds, the method, apparatus and computer program product access a point cloud compression coded bitstream and cause storage of the point cloud compression coded bitstream. The point cloud compression coded bitstream comprises a texture information bitstream, a geometry information bitstream, and an auxiliary metadata bitstream. Relative to the decoding of compressed point clouds, the method, apparatus and computer program product receive a point cloud compression coded bitstream and decode the point cloud compression coded bitstream.

A method, apparatus and computer program product are provided to signal and store compressed point clouds in video encoding. The method, apparatus and computer program product may be utilized in conjunction with a variety of video formats. Relative to encoding of compressed point clouds, the method, apparatus and computer program product access a point cloud compression coded bitstream and cause storage of the point cloud compression coded bitstream. The point cloud compression coded bitstream comprises a texture information bitstream, a geometry information bitstream, and an auxiliary metadata bitstream. Relative to the decoding of compressed point clouds, the method, apparatus and computer program product receive a point cloud compression coded bitstream and decode the point cloud compression coded bitstream.