Bird's Eye View (BEV) is a popular representation for processing 3D point clouds, and by its nature is fundamentally sparse. Motivated by the computational limitations of mobile robot platforms, we create a fast, high-performance BEV 3D object detector that maintains and exploits this input sparsity to decrease runtimes over non-sparse baselines and avoids the tradeoff between pseudoimage area and runtime. We present results on KITTI, a canonical 3D detection dataset, and Matterport-Chair, a novel Matterport3D-derived chair detection dataset from scenes in real furnished homes. We evaluate runtime characteristics using a desktop GPU, an embedded ML accelerator, and a robot CPU, demonstrating that our method results in significant detection speedups (2X or more) for embedded systems with only a modest decrease in detection quality. Our work represents a new approach for practitioners to optimize models for embedded systems by maintaining and exploiting input sparsity throughout their entire pipeline to reduce runtime and resource usage while preserving detection performance.
@article{arxiv.2106.06882,
title = {Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems},
author = {Kyle Vedder and Eric Eaton},
journal= {arXiv preprint arXiv:2106.06882},
year = {2022}
}
Comments
7 pages, 5 figures. Submitted to IROS 2022. All models, weights, experimental configurations, and datasets used are publicly available at http://vedder.io/sparse_point_pillars