Abstract: Method and apparatus for compressing lidar data provide for obtaining to-be-compressed data, where the to-be-compressed data is measurement data collected by lidar through N transmissions, where N?1. When the to-be-compressed data includes corresponding distance measurement data and signal intensity measurement data, the distance measurement data is compressed to obtain a first bitstream. Signal intensity measurement data is predicted based on the distance measurement data to obtain a second bitstream.

Abstract: A point cloud data coding method and related coding devices are provided. The method comprises: obtaining an N-ary a tree representation of point cloud data; determining probabilities for entropy coding of information associated with of a current node of the tree, including: selecting a neural network, out of two or more pretrained neural networks, according to a level of the current node within the tree, obtaining the probabilities by processing input data related to the current node by the selected neural network; and entropy coding of the information associated with the current node using the determined probabilities.

Abstract: Methods and apparatuses are provided for entropy encoding and decoding data of a three-dimensional point cloud, which includes for a current node in an N-ary tree-structure representing the three-dimensional point cloud, extracting features of a set of the neighboring nodes of the current node by applying a neural network including an attention layer. Probabilities of information associated with the current node is estimated based on the extracted features. The information associated with the current node is entropy encoded based on the estimated probabilities.

Abstract: An apparatus and a method for decoding a 3D map, and an encoded bitstream of a 3D map are provided. The apparatus for decoding a 3D map includes a transmitter and a decompressor. The transmitter is configured to receive a bitstream of a 3D map, where the 3D map includes a plurality of 3D map points. The decompressor is configured to decompress the bitstream of the 3D map to obtain reconstructed data of the 3D map, where the reconstructed data of the 3D map includes reconstructed data of the plurality of 3D map points. In this application, the decompressor end may support decompression of compressed data of the 3D map, to support compression/decompression of data of the 3D map.

Abstract: A three-dimensional (3D) map compression method includes performing compaction processing on a to-be-encoded descriptor to obtain a first compact representation of the to-be-encoded descriptor, where the to-be-encoded descriptor corresponds to at least one 3D map point on a 3D map. A compact representation of at least one reference descriptor corresponding to the to-be-encoded descriptor is obtained, followed by obtaining a second compact representation of the to-be-encoded descriptor based on the first compact representation of the to-be-encoded descriptor and the compact representation of the at least one reference descriptor and encapsulating the second compact representation to obtain a bitstream of the 3D map.

Abstract: An apparatus and a method for encoding a 3D map are provided. The apparatus for encoding a 3D map includes a compression module (51) and a transmission module (52). The compression module (51) is configured to compress data of a 3D map to obtain a bitstream of the 3D map, where the 3D map includes a plurality of 3D map points, and the data of the 3D map includes data of the plurality of 3D map points. The transmission module (52) is configured to transmit the bitstream of the 3D map. With the use of the apparatus, a data volume of a 3D map can be reduced, thereby reducing transmission bandwidth and improving transmission efficiency.