Junhua Long — accepted AI-conference papers

2024

A Du-Octree based Cross-Attention Model for LiDAR Geometry Compression

Mingyue Cui, Mingjian Feng, Junhua Long, Daosong Hu, Shuai Zhao, Kai Huang

ICRA 2024poster

Point cloud compression is an essential technology for efficient storage and transmission of 3D data. Previous methods usually use hierarchical tree data structures for encoding the spatial sparseness of point clouds. However, the node context within the tree is not fully discovered since the featur…

Cited by 4 Source ↗Scholar ↗

2023

OctFormer: Efficient Octree-Based Transformer for Point Cloud Compression with Local Enhancement

Mingyue Cui, Junhua Long, Mingjian Feng, Boyang Li, Huang Kai

AAAI 2023technical

Point cloud compression with a higher compression ratio and tiny loss is essential for efficient data transportation. However, previous methods that depend on 3D convolution or frequent multi-head self-attention operations bring huge computations. To address this problem, we propose an octree-based…

Cited by 25 Source ↗PDF ↗Scholar ↗