Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization

Lahav Lipson, Jia Deng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We introduce a new system for Multi-Session SLAM, which tracks camera motion across multiple disjoint videos under a single global reference. Our approach couples the prediction of optical flow with solver layers to estimate camera pose. The backbone is trained end-to-end using a novel differentiable solver for wide-baseline two-view pose. The full system can connect disjoint sequences, perform visualodometry, and global optimization. Compared to existing approaches, our design is accurate and robust to catas-trophic failures. Code is available at https://github.com/princeton-v1/MultiSlam-DiffPose

Original languageEnglish (US)
Title of host publicationProceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024
PublisherIEEE Computer Society
Pages19626-19635
Number of pages10
ISBN (Electronic)9798350353006
DOIs
StatePublished - 2024
Event2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 - Seattle, United States
Duration: Jun 16 2024Jun 22 2024

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Conference

Conference2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024
Country/TerritoryUnited States
CitySeattle
Period6/16/246/22/24

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Keywords

  • Camera Pose
  • Odometry
  • SLAM
  • Tracking

Fingerprint

Dive into the research topics of 'Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization'. Together they form a unique fingerprint.

Cite this