i3dLoc: Image-to-range Cross-domain Localization Robust to Inconsistent Environmental Conditions

@article{Yin2021i3dLocIC,
  title={i3dLoc: Image-to-range Cross-domain Localization Robust to Inconsistent Environmental Conditions},
  author={Peng Yin and Lingyun Xu and Ji Zhang and Sebastian A. Scherer},
  journal={ArXiv},
  year={2021},
  volume={abs/2105.12883}
}
We present a method for localizing a single camera with respect to a point cloud map in indoor and outdoor scenes. The problem is challenging because correspondences of local invariant features are inconsistent across the domains between image and 3D. The problem is even more challenging as the method must handle various environmental conditions such as illumination, weather, and seasonal changes. Our method can match equirectangular images to the 3D range projections by extracting cross-domain… 

iSimLoc: Visual Global Localization for Previously Unseen Environments with Simulated Images

TLDR
iSimLoc is presented, a condition/viewpoint consistent hierarchical global re-localization approach that can be utilized to search target images under changing appearances and viewpoints and achieves robust localization in a range of environments.

Contrastive Learning of Features between Images and LiDAR

TLDR
This work proposes a Tuple-Circle loss function for cross-modality feature learning and developed a variant of widely used PointNet++ architecture for point cloud and U-Net CNN architecture for images to learn good features and not lose generality.

General Place Recognition Survey: Towards the Real-world Autonomy Age

TLDR
This paper starts by investigating the formulation of place recognition in long-term autonomy and the major challenges in real-world environments, and reviews the recent works in place recognition for different sensor modalities and current strategies for dealing with various place recognition challenges.

BioSLAM: A Bio-inspired Lifelong Memory System for General Place Recognition

TLDR
BioSLAM is the first memory-enhanced lifelong SLAM system to help incremental place recognition in long-term navigation tasks and provides a novel dual-memory mechanism for maintenance.

References

SHOWING 1-10 OF 17 REFERENCES

2D3D-Matchnet: Learning To Match Keypoints Across 2D Image And 3D Point Cloud

TLDR
The 2D3D-MatchNet is proposed - an end-to-end deep network architecture to jointly learn the descriptors for 2D and 3D keypoint from image and point cloud, respectively.

Convolutional neural network-based coarse initial position estimation of a monocular camera in large-scale 3D light detection and ranging maps

TLDR
This work proposes a novel approach that estimates the initial position of a monocular camera within a given 3D light detection and ranging map using a convolutional neural network with no retraining is required, and uses an unsupervised learning framework to predict the depth from a single image.

LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis

  • Zhe LiuShunbo Zhou Yunhui Liu
  • Computer Science, Environmental Science
    2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
TLDR
A novel deep neural network, named LPD-Net (Large-scale Place Description Network), which can extract discriminative and generalizable global descriptors from the raw 3D point cloud and reaches the state-of-the-art.

PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition

TLDR
This paper proposes a combination/modification of the existing PointNet and NetVLAD, which allows end-to-end training and inference to extract the global descriptor from a given 3D point cloud, and proposes the "lazy triplet and quadruplet" loss functions that can achieve more discriminative and generalizable global descriptors to tackle the retrieval task.

OverlapNet: Loop Closing for LiDAR-based SLAM

TLDR
This paper addresses the problem of loop closing for SLAM based on 3D laser scans recorded by autonomous cars by utilizing a deep neural network exploiting different cues generated from LiDAR data for finding loop closures.

NetVLAD: CNN Architecture for Weakly Supervised Place Recognition

TLDR
A convolutional neural network architecture that is trainable in an end-to-end manner directly for the place recognition task and an efficient training procedure which can be applied on very large-scale weakly labelled tasks are developed.

Vehicle model based visual-tag monocular ORB-SLAM

TLDR
A vehicle model based monocular ORBSLAM method supplemented by April-Tag to improve the performance of original algorithm and is practical when autonomous driving in low-light and less-feature environment like garages and tunnels.

Line-Based 2-D–3-D Registration and Camera Localization in Structured Environments

TLDR
This article proposes a new 2-D–3-D registration method to estimate 1-D-2-D line feature correspondences and the camera pose in untextured point clouds of structured environments and demonstrates the effectiveness on the synthetic and real data set with repeated structures and rapid depth changes.

Spherical CNNs

TLDR
A definition for the spherical cross-correlation is proposed that is both expressive and rotation-equivariant and satisfies a generalized Fourier theorem, which allows us to compute it efficiently using a generalized (non-commutative) Fast Fourier Transform (FFT) algorithm.

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAM

TLDR
This article presents ORB-SLAM3, the first system able to perform visual, visual-inertial and multimap SLAM with monocular, stereo and RGB-D cameras, using pin-hole and fisheye lens models, resulting in real-time robust operation in small and large, indoor and outdoor environments.