Comparative Design Space Exploration of Dense and Semi-Dense SLAM

TL;DR

This paper compares two advanced SLAM systems, KinectFusion and LSD-SLAM, across accuracy, energy, and speed metrics on different hardware, while analyzing their internal kernels for design insights.

Contribution

It extends the SLAMBench framework to enable comprehensive quantitative comparison and kernel-level analysis of SLAM pipelines on multiple hardware platforms.

Findings

KinectFusion and LSD-SLAM show different trade-offs in accuracy and energy consumption.

Kernel-level analysis reveals distinct algorithmic and hardware design characteristics.

Benchmarking across platforms provides insights for optimizing SLAM systems.

Abstract

SLAM has matured significantly over the past few years, and is beginning to appear in serious commercial products. While new SLAM systems are being proposed at every conference, evaluation is often restricted to qualitative visualizations or accuracy estimation against a ground truth. This is due to the lack of benchmarking methodologies which can holistically and quantitatively evaluate these systems. Further investigation at the level of individual kernels and parameter spaces of SLAM pipelines is non-existent, which is absolutely essential for systems research and integration. We extend the recently introduced SLAMBench framework to allow comparing two state-of-the-art SLAM pipelines, namely KinectFusion and LSD-SLAM, along the metrics of accuracy, energy consumption, and processing frame rate on two different hardware platforms, namely a desktop and an embedded device. We also analyze the pipelines at the level of individual kernels and explore their algorithmic and hardware design spaces for the first time, yielding valuable insights.