Granted Patent B2

US 12,694,574 · App. 18/632,140 · Granted Jul 28, 2026

Inventors: Anique Akhtar (San Diego, CA); Geert Van der Auwera (San Diego, CA); Adarsh Krishnan Ramasubramonian (Irvine, CA); Marta Karczewicz (San Diego, CA)

Assignee: QUALCOMM Incorporated

G06T9/002G06T9/40G06T17/00G06T2210/32G06T2210/56

Abstract

Claims (42)

1 . A device for decoding point cloud data, the device comprising:

a memory configured to store point cloud data; and

a processing system comprising one or more processors implemented in circuitry, the processing system being configured to:

decode encoded point cloud geometry data for a point cloud to form reconstructed point cloud geometry data for the point cloud;

downscale the reconstructed point cloud geometry data to form downscaled point cloud geometry data;

decode encoded attribute data for the point cloud using the downscaled point cloud geometry data to form decoded attribute data;

apply the decoded attribute data to the reconstructed point cloud geometry data to form intermediate point cloud data; and

apply a residual learning network to the intermediate point cloud data to form a reconstructed point cloud.

2 . The device of claim 1 , wherein the processing system is further configured to decode a value representing an amount of downscaling to be applied to the point cloud geometry data, wherein to downscale the point cloud geometry data, the one or more processors are configured to downscale the point cloud geometry data according to the value representing the amount of downscaling.

3 . The device of claim 2 , wherein the one or more processors are configured to provide the value representing the amount of downscaling to be applied to the point cloud geometry data to the residual learning network.

4 . The device of claim 2 , wherein the one or more processors are configured to select the residual learning network from a plurality of residual learning networks according to the value representing the amount of downscaling to be applied to the point cloud geometry data.

5 . The device of claim 1 , wherein the residual learning network includes one or more convolutional neural network layers and a combination unit that combines output of the one or more convolutional neural network layers with the intermediate point cloud data to form the reconstructed point cloud.

6 . The device of claim 1 , wherein the residual learning network comprises a first residual learning network, and wherein the processing system is further configured to apply a second residual learning network during pre-processing or as a filter to the point cloud.

7 . The device of claim 1 , wherein the decoded attribute data includes color data in one of a red-green-blue (RGB) format or a luminance, blue hue chrominance, and red hue chrominance (YCbCr) format.

8 . The device of claim 1 , wherein to downscale the point cloud geometry data, the processing system is configured to:

for each node of an octree that includes eight leaf sub-nodes where at least one of the eight leaf sub-nodes is occupied by a point, redefine the node as an occupied leaf node in a downscaled octree; and

for each node of the octree that includes eight leaf sub-nodes where none of the eight leaf sub-nodes is occupied by a point, redefine the node as an unoccupied leaf node in the downscaled octree.

9 . The device of claim 1 , wherein to downscale the point cloud geometry data, the processing system is configured to:

for each node of an octree that includes eight leaf sub-nodes where a number of the eight leaf sub-nodes that is occupied is greater than a threshold, redefine the node as an occupied leaf node in a downscaled octree; and

for each node of the octree that includes eight leaf sub-nodes where a number of the eight leaf sub-nodes that is occupied is less than or equal to the threshold, redefine the node as an unoccupied leaf node in the downscaled octree.

10 . The device of claim 1 , further comprising a display configured to visually depict the reconstructed point cloud.

11 . A method of decoding point cloud data, the method comprising:

decoding encoded point cloud geometry data for a point cloud to form reconstructed point cloud geometry data for the point cloud;

downscaling the reconstructed point cloud geometry data to form downscaled point cloud geometry data;

decoding encoded attribute data for the point cloud using the downscaled point cloud geometry data to form decoded attribute data;

applying the decoded attribute data to the reconstructed point cloud geometry data to form intermediate point cloud data; and

applying a residual learning network to the intermediate point cloud data to form a reconstructed point cloud.

12 . The method of claim 11 , further comprising decoding a value representing an amount of downscaling to be applied to the point cloud geometry data, wherein downscaling the point cloud geometry data includes downscaling the point cloud geometry data according to the value representing the amount of downscaling.

13 . The method of claim 12 , further comprising providing the value representing the amount of downscaling to be applied to the point cloud geometry data to the residual learning network.

14 . The method of claim 12 , further comprising selecting the residual learning network from a plurality of residual learning networks according to the value representing the amount of downscaling to be applied to the point cloud geometry data.

15 . The method of claim 11 , wherein the residual learning network includes one or more convolutional neural network layers and a combination unit that combines output of the one or more convolutional neural network layers with the intermediate point cloud data to form the reconstructed point cloud.

16 . The method of claim 11 , wherein the residual learning network comprises a first residual learning network, the method further comprising applying a second residual learning network during pre-processing or as a filter to the point cloud.

17 . The method of claim 11 , wherein the attribute data includes color data in one of a red-green-blue (RGB) format or a luminance, blue hue chrominance, and red hue chrominance (YCbCr) format.

18 . The method of claim 11 , wherein downscaling the point cloud geometry data comprises:

for each node of an octree that includes eight leaf sub-nodes where at least one of the eight leaf sub-nodes is occupied by a point, redefining the node as an occupied leaf node in a downscaled octree; and

for each node of the octree that includes eight leaf sub-nodes where none of the eight leaf sub-nodes is occupied by a point, redefining the node as an unoccupied leaf node in the downscaled octree.

19 . The method of claim 11 , wherein downscaling the point cloud geometry data comprises:

for each node of an octree that includes eight leaf sub-nodes where a number of the eight leaf sub-nodes that is occupied is greater than a threshold, redefining the node as an occupied leaf node in a downscaled octree; and

for each node of the octree that includes eight leaf sub-nodes where a number of the eight leaf sub-nodes that is occupied is less than or equal to the threshold, redefining the node as an unoccupied leaf node in the downscaled octree.

20 . The method of claim 11 , further comprising:

decoding a value representing an amount of downscaling to be applied to the point cloud geometry data, wherein downscaling the point cloud geometry data comprises downscaling the point cloud geometry data according to the value representing the amount of downscaling; and

providing the value representing the amount of downscaling to be applied to the point cloud geometry data to the residual learning network.

Assignments (1)

Continuity (2)

References Cited (26)