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

Abstract

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 Transformer compression method called OctFormer, which does not rely on the occupancy information of sibling nodes. Our method uses non-overlapped context windows to construct octree node sequences and share the result of a multi-head self-attention operation among a sequence of nodes. Besides, we introduce a locally-enhance module for exploiting the sibling features and a positional encoding generator for enhancing the translation invariance of the octree node sequence. Compared to the previous state-of-the-art works, our method obtains up to 17% Bpp savings compared to the voxel-context-based baseline and saves an overall 99% coding time compared to the attention-based baseline.

SCP: Spherical-Coordinate-Based Learned Point Cloud Compression

“…OctSqueeze (Huang et al 2020) builds the Octree of the point cloud, predicting voxel occupancy level by level, using information from ancient voxels and known data about the current voxel. Building upon OctSqueeze, methods such as VoxelDNN (Nguyen et al 2021a), VoxelContext-Net (Que, Lu, and Xu 2021), SparsePCGC (Wang et al 2022), and OctFormer (Cui et al 2023) eliminate redundancy by employing the information of neighbor voxels of the parent voxel. Moreover, Surface Prior (Chen et al 2022) incorporates neighbor voxels which share the same depth as the current coding voxel, into the framework.…”

“…Concurrently, learned point cloud compression methods are emerging, using deep learning techniques to compress point clouds. Former work such as OctSqueeze (Huang et al 2020), VoxelDNN (Nguyen et al 2021a), VoxelContext-Net (Que, Lu, and Xu 2021), and OctFormer (Cui et al 2023) employ information of ancient voxels for prediction of the current one. Advancing these approaches, OctAttention (Fu et al 2022), SparsePCGC (Wang et al 2022), and EHEM (Song et al 2023) harness the voxels in the same level as the current one to minimize the redundancy.…”

Automated Reconstruction of Existing Building Interior Scene BIMs Using a Feature-Enhanced Point Transformer and an Octree

“…It can efficiently process and manage 3D data, providing rapid search and segmentation outcomes, making objection segmentation tasks more efficient and accurate. The octree algorithm is currently applied in point cloud compression [39]), surface reconstruction [40], and other fields. This study achieved objection segmentation-based semantic segmentation results through octree, providing data support for the subsequent establishment of the monomer BIM.…”