Saved in:
Bibliographic Details
Main Authors: Gottam, Sai Puneeth Reddy, Zhang, Haoming, Keras, Eivydas
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.08333
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908530055839744
author Gottam, Sai Puneeth Reddy
Zhang, Haoming
Keras, Eivydas
author_facet Gottam, Sai Puneeth Reddy
Zhang, Haoming
Keras, Eivydas
contents Visual-based localization has made significant progress, yet its performance often drops in large-scale, outdoor, and long-term settings due to factors like lighting changes, dynamic scenes, and low-texture areas. These challenges degrade feature extraction and tracking, which are critical for accurate motion estimation. While learning-based methods such as SuperPoint and SuperGlue show improved feature coverage and robustness, they still face generalization issues with out-of-distribution data. We address this by enhancing deep feature extraction and tracking through self-supervised learning with task specific feedback. Our method promotes stable and informative features, improving generalization and reliability in challenging environments.
format Preprint
id arxiv_https___arxiv_org_abs_2509_08333
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Good Deep Features to Track: Self-Supervised Feature Extraction and Tracking in Visual Odometry
Gottam, Sai Puneeth Reddy
Zhang, Haoming
Keras, Eivydas
Robotics
Computer Vision and Pattern Recognition
Visual-based localization has made significant progress, yet its performance often drops in large-scale, outdoor, and long-term settings due to factors like lighting changes, dynamic scenes, and low-texture areas. These challenges degrade feature extraction and tracking, which are critical for accurate motion estimation. While learning-based methods such as SuperPoint and SuperGlue show improved feature coverage and robustness, they still face generalization issues with out-of-distribution data. We address this by enhancing deep feature extraction and tracking through self-supervised learning with task specific feedback. Our method promotes stable and informative features, improving generalization and reliability in challenging environments.
title Good Deep Features to Track: Self-Supervised Feature Extraction and Tracking in Visual Odometry
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.08333