Method and apparatus for point cloud compression

1. A method for point cloud decompression, comprising:

decoding, by a processor using a video coding algorithm, prediction information of a point cloud from a coded bitstream;

reconstructing, by the processor, a geometry reconstructed cloud according to a two-dimensional geometry image of the point cloud, the geometry image being decoded from the coded bitstream;

selecting, by the processor, at least one geometry sample inside a patch of the geometry reconstructed cloud, the selecting being based on a comparison between a threshold value and motion vectors corresponding to geometry samples inside the patch such that the selected at least one geometry sample corresponds to at least one pixel having a motion vector larger than the threshold value;

applying, by the processor, a filter to the selected at least one geometry sample inside the patch of the geometry reconstructed cloud and applying the filter to boundary samples of the patch to generate a smoothed geometry reconstructed cloud; and

reconstructing, by the processor, points of the point cloud based on the smoothed geometry reconstructed cloud such that the reconstructed points of the point cloud represent a three-dimensional space based on the coded bitstream.

2. The method of claim 1 , wherein the selecting includes selecting, by the processor and based on the motion vectors corresponding to the geometry samples inside the patch, an area inside the patch with a level of motion content higher than a threshold level among depth values of geometry samples in the area, the motion vectors being provided as part of the video coding algorithm standard, and

the applying includes applying the filter to the selected area.

3. The method of claim 1 , wherein the selecting includes detecting, by the processor, edges inside the patch based on depth values of the geometry reconstructed cloud, and

the applying includes applying the filter to the detected edges.

4. The method of claim 1 , wherein the prediction information includes a flag indicating whether selective smoothing was applied inside patches of the geometry reconstructed cloud.

5. The method of claim 4 , wherein the prediction information is indicative of a specific algorithm used to select points inside the patches for the selective smoothing.

6. The method of claim 5 , wherein the prediction information includes parameters for the specific algorithm.

7. A method for point cloud compression, comprising:

compressing, by a processor using a video coding algorithm, a two-dimensional geometry image associated with a point cloud;

reconstructing, by the processor, a geometry reconstructed cloud according to the compressed geometry image of the point cloud;

selecting, by the processor, at least one geometry sample inside a patch of the geometry reconstructed cloud, the selecting being based on a comparison between a threshold value and motion vectors corresponding to geometry samples inside the patch such that the selected at least one geometry sample corresponds to at least one pixel having a motion vector larger than the threshold value;

applying, by the processor, a filter to the selected at least one geometry sample inside the patch of the geometry reconstructed cloud and applying the filter to boundary samples of the patch to generate a smoothed geometry reconstructed cloud; and

generating, by the processor, a texture image for the point cloud based on the smoothed geometry reconstructed cloud such that the compressed geometry image and the texture image are used to generate a coded bitstream representing the point cloud.

8. The method of claim 7 , wherein

the selecting includes selecting, by the processor and based on the motion vectors corresponding to the geometry samples inside the patch, an area inside the patch with a level of motion content higher than a threshold level among depth values of geometry samples in the area, the motion vectors being provided as part of the video coding standard, and

the applying includes applying the filter to the selected area.

9. The method of claim 8 , wherein

the selecting includes detecting, by the processor, edges inside the patch based on depth values of the geometry reconstructed cloud, and

the applying includes applying the filter to the detected edges.

10. The method of claim 7 , further comprising:

including, in the coded bitstream, a flag indicating whether selective smoothing was applied inside patches of the geometry reconstructed cloud.

11. The method of claim 10 , further comprising:

including, in the coded bitstream, an indicator indicative of a specific algorithm used to select points inside the patches to apply the selective smoothing.

12. An apparatus for point cloud decompression, comprising:

processing circuitry configured to:

decode, using a video coding algorithm, prediction information of a point cloud from a coded bitstream;

reconstruct a geometry reconstructed cloud according to a two-dimensional geometry image of the point cloud, the geometry image being decoded from the coded bitstream;

select at least one geometry sample inside a patch of the geometry reconstructed cloud, the selecting being based on a comparison between a threshold value and motion vectors corresponding to geometry samples inside the patch such that the selected at least one geometry sample corresponds to at least one pixel having a motion vector larger than the threshold value;

apply a filter to the selected at least one geometry sample inside the patch of the geometry reconstructed cloud and applying the filter to boundary samples of the patch to generate a smoothed geometry reconstructed cloud; and

reconstruct points of the point cloud based on the smoothed geometry reconstructed cloud such that the reconstructed points of the point cloud represent a three-dimensional space based on the coded bitstream.

13. The apparatus of claim 12 , wherein

the processing circuitry is configured to select, based on the motion vectors corresponding to the geometry samples inside the patch, the at least one geometry sample by selecting an area inside the patch with a level of motion content higher than a threshold level among depth values of geometry samples in the area, the motion vectors being provided as part of the video coding standard, and

the processing circuitry is configured to apply the filter by applying the filter to the selected area.

14. The apparatus of claim 12 , wherein

the processing circuitry is configured to select the at least one geometry sample by detecting edges inside the patch based on depth values of the geometry reconstructed cloud; and

the processing circuitry is configured to apply the filter by applying the filter to the detected edges.