A dynamic memory assignment strategy for dilation-based ICP algorithm on embedded GPUs

TL;DR

This paper introduces a memory-efficient optimization for VANICP, enabling its deployment on embedded GPUs by significantly reducing memory usage while maintaining high performance in point cloud registration.

Contribution

It presents a dynamic memory assignment strategy tailored for dilation-based ICP on embedded GPUs, reducing memory consumption by over 97% without performance loss.

Findings

Achieved over 97% reduction in memory usage.

Maintained original registration performance.

Enabled lightweight deployment on embedded GPUs.

Abstract

This paper proposes a memory-efficient optimization strategy for the high-performance point cloud registration algorithm VANICP, enabling lightweight execution on embedded GPUs with constrained hardware resources. VANICP is a recently published acceleration framework that significantly improves the computational efficiency of point-cloud-based applications. By transforming the global nearest neighbor search into a localized process through a dilation-based information propagation mechanism, VANICP greatly reduces the computational complexity of the NNS. However, its original implementation demands a considerable amount of memory, which restricts its deployment in resource-constrained environments such as embedded systems. To address this issue, we propose a GPU-oriented dynamic memory assignment strategy that optimizes the memory usage of the dilation operation. Furthermore, based on this strategy, we construct an enhanced version of the VANICP framework that achieves over 97% reduction in memory consumption while preserving the original performance. Source code is published on: https://github.com/changqiong/VANICP4Em.git.