Deep Patch Visual SLAM

TL;DR

DPV-SLAM is a monocular visual SLAM method optimized for single GPU use, achieving real-time performance with high accuracy and low memory overhead, suitable for practical deployment.

Contribution

It introduces DPV-SLAM, a GPU-efficient visual SLAM system that maintains high framerates and accuracy comparable to state-of-the-art methods, with significantly reduced resource requirements.

Findings

Runs at 1x-4x real-time framerates on real-world datasets

Achieves accuracy comparable to DROID-SLAM

Uses only 5-7G memory, 2.5x faster than existing methods

Abstract

Recent work in visual SLAM has shown the effectiveness of using deep network backbones. Despite excellent accuracy, however, such approaches are often expensive to run or do not generalize well zero-shot. Their runtime can also fluctuate wildly while their frontend and backend fight for access to GPU resources. To address these problems, we introduce Deep Patch Visual (DPV) SLAM, a method for monocular visual SLAM on a single GPU. DPV-SLAM maintains a high minimum framerate and small memory overhead (5-7G) compared to existing deep SLAM systems. On real-world datasets, DPV-SLAM runs at 1x-4x real-time framerates. We achieve comparable accuracy to DROID-SLAM on EuRoC and TartanAir while running 2.5x faster using a fraction of the memory. DPV-SLAM is an extension to the DPVO visual odometry system; its code can be found in the same repository: https://github.com/princeton-vl/DPVO