ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2407.08023
18
0

Hybrid Structure-from-Motion and Camera Relocalization for Enhanced Egocentric Localization

10 July 2024
Jinjie Mai
Abdullah Hamdi
Silvio Giancola
Chen Zhao
Bernard Ghanem
    EgoV
ArXivPDFHTML
Abstract

We built our pipeline EgoLoc-v1, mainly inspired by EgoLoc. We propose a model ensemble strategy to improve the camera pose estimation part of the VQ3D task, which has been proven to be essential in previous work. The core idea is not only to do SfM for egocentric videos but also to do 2D-3D matching between existing 3D scans and 2D video frames. In this way, we have a hybrid SfM and camera relocalization pipeline, which can provide us with more camera poses, leading to higher QwP and overall success rate. Our method achieves the best performance regarding the most important metric, the overall success rate. We surpass previous state-of-the-art, the competitive EgoLoc, by 1.5%1.5\%1.5%. The code is available at \url{https://github.com/Wayne-Mai/egoloc_v1}.

View on arXiv
Comments on this paper