HgPCN: A Heterogeneous Architecture for E2E Embedded Point Cloud Inference

TL;DR

HgPCN is a novel end-to-end heterogeneous architecture designed for real-time embedded point cloud inference, addressing latency bottlenecks in pre-processing and data structuring through innovative spatial indexing techniques.

Contribution

The paper introduces two novel spatial indexing methodologies, Octree-Indexed-Sampling and Voxel-Expanded Gathering, to significantly reduce latency in end-to-end point cloud processing on edge devices.

Findings

Achieves real-time performance in embedded point cloud applications.

Reduces memory and computational bottlenecks in pre-processing and inference.

Demonstrates improved efficiency over existing approaches.

Abstract

Point cloud is an important type of geometric data structure for many embedded applications such as autonomous driving and augmented reality. Current Point Cloud Networks (PCNs) have proven to achieve great success in using inference to perform point cloud analysis, including object part segmentation, shape classification, and so on. However, point cloud applications on the computing edge require more than just the inference step. They require an end-to-end (E2E) processing of the point cloud workloads: pre-processing of raw data, input preparation, and inference to perform point cloud analysis. Current PCN approaches to support end-to-end processing of point cloud workload cannot meet the real-time latency requirement on the edge, i.e., the ability of the AI service to keep up with the speed of raw data generation by 3D sensors. Latency for end-to-end processing of the point cloud workloads stems from two reasons: memory-intensive down-sampling in the pre-processing phase and the data structuring step for input preparation in the inference phase. In this paper, we present HgPCN, an end-to-end heterogeneous architecture for real-time embedded point cloud applications. In HgPCN, we introduce two novel methodologies based on spatial indexing to address the two identified bottlenecks. In the Pre-processing Engine of HgPCN, an Octree-Indexed-Sampling method is used to optimize the memory-intensive down-sampling bottleneck of the pre-processing phase. In the Inference Engine, HgPCN extends a commercial DLA with a customized Data Structuring Unit which is based on a Voxel-Expanded Gathering method to fundamentally reduce the workload of the data structuring step in the inference phase.