Method for predicting point cloud attribute, encoder, decoder, and storage medium
AssigneeTencent Technology (Shenzhen) Company Limited
InventorWenjie Zhu
Life of this patent
Estimating the term…
Abstract
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.
Claims20
A method for predicting a point cloud attribute, the method comprising:
- acquiring, by a device comprising a memory storing instructions and a processor in communication with the memory, N encoded points closest to a target point from point cloud data as N adjacent points of the target point, the target point being one of points in the point cloud data;
- acquiring, by the device, K first-group adjacent points from the N adjacent points, the K first-group adjacent points comprising M repetition points with same position information;
- determining, by the device, at least one target adjacent point of the target point according to the M repetition points;
- and
- performing, by the device, attribute prediction on the target point according to reconstructed attribute information of the at least one target adjacent point,
- wherein each of N, K, and M is a positive integer.
An apparatus for predicting a point cloud attribute, the apparatus comprising:
- a memory storing instructions;
- and
- a processor in communication with the memory, wherein, when the processor executes the instructions, the processor is configured to cause the apparatus to perform:
- acquiring N encoded points closest to a target point from point cloud data as N adjacent points of the target point, the target point being one of points in the point cloud data;
- acquiring K first-group adjacent points from the N adjacent points, the K first-group adjacent points comprising M repetition points with same position information;
- determining at least one target adjacent point of the target point according to the M repetition points;
- and
- performing attribute prediction on the target point according to reconstructed attribute information of the at least one target adjacent point,
- wherein each of N, K, and M is a positive integer.
A non-transitory computer-readable storage medium, configured to store computer-readable instructions, wherein, the computer-readable instructions, when executed by a processor, are configured to cause the processor to perform:
- acquiring N encoded points closest to a target point from point cloud data as N adjacent points of the target point, the target point being one of points in the point cloud data;
- acquiring K first-group adjacent points from the N adjacent points, the K first-group adjacent points comprising M repetition points with same position information;
- determining at least one target adjacent point of the target point according to the M repetition points;
- and
- performing attribute prediction on the target point according to reconstructed attribute information of the at least one target adjacent point, wherein each of N, K, and M is a positive integer.
Dependencies are inferred from the claim text.