Abstract: An example device for decoding point cloud data includes: a memory configured to store point cloud data; and one or more processors implemented in circuitry and 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 point cloud geometry data to form downscaled point cloud geometry data; decode attribute data for the point cloud using the downscaled point cloud geometry; apply the 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.

Abstract: An example device for coding point cloud data includes: a memory configured to store point cloud data; and one or more processors implemented in circuitry and configured to: decode encoded point cloud geometry data for a point cloud to reconstruct point cloud geometry data for the point cloud; downscale the point cloud geometry data to form downscaled point cloud geometry data; and code attribute data for the point cloud using the downscaled point cloud geometry. When encoding the attribute data, the processors may encode the point cloud geometry data using a deep learning-based geometry encoder. When decoding the attribute data, the processors may upscale the downscaled point cloud attribute data. The processors may code a value representing an amount of downscaling to apply to the decoded point cloud geometry data.

Abstract: A method of encoding point cloud data includes receiving, for a first encoding process, geometry data of the point cloud data of a source point cloud; encoding, in accordance with the first encoding process, the geometry data to generate encoded geometry data of a target point cloud and a geometry bitstream; decoding the encoded geometry data to generate reconstructed geometry data; performing an attribute recomputing process on attribute data of the point cloud data of the source point cloud based on the reconstructed geometry data to generate recomputed, reconstructed point cloud data of the target point cloud; and encoding, in accordance with a second encoding process, the recomputed, reconstructed point cloud data to generate an attribute bitstream.

Abstract: A method of encoding point cloud data includes receiving, for a first encoding process, geometry data of the point cloud data of a source point cloud; encoding, in accordance with the first encoding process, the geometry data to generate encoded geometry data of a target point cloud and a geometry bitstream; decoding the encoded geometry data to generate reconstructed geometry data; performing an attribute recomputing process on attribute data of the point cloud data of the source point cloud based on the reconstructed geometry data to generate recomputed, reconstructed point cloud data of the target point cloud; and encoding, in accordance with a second encoding process, the recomputed, reconstructed point cloud data to generate an attribute bitstream.

Abstract: A method, computer program, and computer system is provided for processing point cloud data. Quantized point cloud data including a plurality of voxels is received. An occupancy map is generated for the quantized point cloud corresponding to lost voxels during quantization from among the plurality of voxels. A point cloud is reconstructed from the quantized point cloud data based on populating the lost voxels.

Abstract: An example device for decoding point cloud data includes a memory configured to store point cloud data; and one or more processors implemented in circuitry and configured to: determine a number of times to upscale a downscaled encoded representation of a point cloud geometry; decode the downscaled encoded representation of the point cloud geometry; upscale the downscaled representation of the point cloud geometry the number of times to form an upscaled representation of the point cloud geometry; and reproduce a point cloud using the upscaled representation of the point cloud geometry.

Abstract: A method, computer program, and computer system is provided for processing point cloud data. Quantized point cloud data including a plurality of voxels is received. An occupancy map is generated for the quantized point cloud corresponding to lost voxels during quantization from among the plurality of voxels. A point cloud is reconstructed from the quantized point cloud data based on populating the lost voxels.