LoopNet: A Multitasking Few-Shot Learning Approach for Loop Closure in Large Scale SLAM

Mohammad-Maher Nakshbandi, Ziad Sharawy, Sorin Grigorescu
7/20/2025
cs.CVcs.LG

Official code: RovisLab/LoopDB (7 stars, last commit 2025-03-08). 1 more implementation below.

Abstract

One of the main challenges in the Simultaneous Localization and Mapping (SLAM) loop closure problem is the recognition of previously visited places. In this work, we tackle the two main problems of real-time SLAM systems: 1) loop closure detection accuracy and 2) real-time computation constraints on the embedded hardware. Our LoopNet method is based on a multitasking variant of the classical ResNet architecture, adapted for online retraining on a dynamic visual dataset and optimized for embedded devices. The online retraining is designed using a few-shot learning approach. The architecture provides both an index into the queried visual dataset, and a measurement of the prediction quality. Moreover, by leveraging DISK (DIStinctive Keypoints) descriptors, LoopNet surpasses the limitations of handcrafted features and traditional deep learning methods, offering better performance under varying conditions. Code is available at https://github.com/RovisLab/LoopNet. Additinally, we introduce a new loop closure benchmarking dataset, coined LoopDB, which is available at https://github.com/RovisLab/LoopDB.

View on arXivView PDF

Code Implementations(2)

RovisLab/LoopDBOfficial100%

RovisLab loop detection dataset.

70PythonJan 23, 20251 years ago
RovisLab/LoopNetOfficial100%
GPL-3.0

LoopNet: A Multitasking Few-Shot Learning Approach for Loop Closure in Large Scale SLAM

10PythonJan 22, 20258 months agoGPL-3.0

Similar Papers

DK-SLAM: Monocular Visual SLAM with Deep Keypoint Learning, Tracking and Loop-Closing

82% match2024

A Minimal Subset Approach for Informed Keyframe Sampling in Large-Scale SLAM

80% match1 repo362025

Semi-supervised Vector-Quantization in Visual SLAM using HGCN

79% match2022

SegMatch: Segment based loop-closure for 3D point clouds

79% match1 repo1.1k2016

Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM

79% match1 repo1162023

GV-Bench: Benchmarking Local Feature Matching for Geometric Verification of Long-term Loop Closure Detection

79% match1 repo692024

Cite this paper

@article{nakshbandi2025loopnet,
  title  = {LoopNet: A Multitasking Few-Shot Learning Approach for Loop Closure in Large Scale SLAM},
  author = {Mohammad-Maher Nakshbandi and Ziad Sharawy and Sorin Grigorescu},
  year   = {2025},
  eprint = {2507.15109},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2507.15109v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2507.15109.svg)](https://codeofpaper.com/paper/2507.15109)

Discussion