# Bi-directional Loop Closure for Visual SLAM

arXiv: https://arxiv.org/abs/2204.01524 · HTML: https://mlsanity.com/paper/2204.01524/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 38 references that are in the map.
- First posted on arXiv 1 Apr 2022.

## Builds on (most cited first, 13 of 13)

- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Learning Deconvolution Network for Semantic Segmentation](https://mlsanity.com/paper/1505.04366/) (2015)
- [The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception](https://mlsanity.com/paper/1801.10202/) (2018)
- [Geometric Loss Functions for Camera Pose Regression with Deep Learning](https://mlsanity.com/paper/1704.00390/) (2017)
- [Deep Image Retrieval: Learning global representations for image search](https://mlsanity.com/paper/1604.01325/) (2016)
- [UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning](https://mlsanity.com/paper/1709.06841/) (2017)
- [Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network](https://mlsanity.com/paper/1707.09733/) (2017)
- [On the Performance of ConvNet Features for Place Recognition](https://mlsanity.com/paper/1501.04158/) (2015)
- [LDSO: Direct Sparse Odometry with Loop Closure](https://mlsanity.com/paper/1808.01111/) (2018)
- [Convolutional Neural Network-based Place Recognition](https://mlsanity.com/paper/1411.1509/) (2014)
- [A Photometrically Calibrated Benchmark For Monocular Visual Odometry](https://mlsanity.com/paper/1607.02555/) (2016)
- [Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints](https://mlsanity.com/paper/2007.15122/) (2020)
- [Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/1506.04924/) (2015)

## Built on by (most cited first, 1 of 1)

- [HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion](https://mlsanity.com/paper/2304.00932/) (2023)

## Abstract (arXiv)

A key functional block of visual navigation system for intelligent autonomous vehicles is Loop Closure detection and subsequent relocalisation. State-of-the-Art methods still approach the problem as uni-directional along the direction of the previous motion. As a result, most of the methods fail in the absence of a significantly similar overlap of perspectives. In this study, we propose an approach for bi-directional loop closure. This will, for the first time, provide us with the capability to relocalize to a location even when traveling in the opposite direction, thus significantly reducing long-term odometry drift in the absence of a direct loop. We present a technique to select training data from large datasets in order to make them usable for the bi-directional problem. The data is used to train and validate two different CNN architectures for loop closure detection and subsequent regression of 6-DOF camera pose between the views in an end-to-end manner. The outcome packs a considerable impact and aids significantly to real-world scenarios that do not offer direct loop closure opportunities. We provide a rigorous empirical comparison against other established approaches and evaluate our method on both outdoor and indoor data from the FinnForest dataset and PennCOSYVIO dataset.