Saved in:
Bibliographic Details
Main Authors: Lipson, Lahav, Teed, Zachary, Deng, Jia
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.01654
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911976841543680
author Lipson, Lahav
Teed, Zachary
Deng, Jia
author_facet Lipson, Lahav
Teed, Zachary
Deng, Jia
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2408_01654
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Patch Visual SLAM
Lipson, Lahav
Teed, Zachary
Deng, Jia
Computer Vision and Pattern Recognition
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
title Deep Patch Visual SLAM
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.01654