ICRA-2022-SLAM-paper-list

This repository is a collection of papers related to SLAM for personal research purposes.
Based on Infovoya, categories were sorted by myself.
If there are any missing papers or incorrect information, please feel free to contact me or leave an issue.

The title in bold is outstanding paper.

Table of contents

• ICRA 2022 workshop related to SLAM
• Dataset
• Visual odometry / Visual SLAM / Structure-From-Motion
• Visual-inertial odometry / Visual-inertial SLAM
• Visual localization / Visual place recognition
• LiDAR odometry / LiDAR SLAM
• LiDAR-inertial odometry / LiDAR-inertial SLAM
• LiDAR localization / LiDAR place recognition
• Point cloud registration
• Sensor fusion
• Inertial odometry
• WiFi SLAM / WiFi Structure-From-Motion
• Collaborative SLAM
• Scene Flow

ICRA 2022 workshop related to SLAM

• Robotic Perception and Mapping: Emerging Techniques - Website
• Future of Construction: Build Faster, Better, Safer - Together with Robots - Website
• 6TH WORKSHOP ON LEGGED ROBOTS - Website
• Canonical DIY Tutorials on Non-Gaussian SLAM and Computation - Website

[top]

Dataset

• M2DGR: A Multi-Sensor and Multi-Scenario SLAM Dataset for Ground Robots

Visual odometry / Visual SLAM / Structure-From-Motion

• Burst Imaging for Light-Constrained Structure-From-Motion
• Self-Supervised Depth and Ego-Motion Estimation for Monocular Thermal Video Using Multi-Spectral Consistency Loss
• LoopNet: Where to Focus? Detecting Loop Closures in Dynamic Scenes
• SimVODIS++: Neural Semantic Visual Odometry in Dynamic Environments
• PANet: A Novel Pixel-Level Attention Network for 6D Pose Estimation with Embedding Vector Features
• Overhead Image Factors for Underwater Sonar-Based SLAM
• MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints
• Non-Penetration Iterative Closest Points for Single-View Multi-Object 6D Pose Estimation
• Translating Images into Maps
• EDPLVO: Efficient Direct Point-Line Visual Odometry
• DEVO: Depth-Event Camera Visual Odometry in Challenging Conditions
• Precise 3D Reconstruction of Plants from UAV Imagery Combining Bundle Adjustment and Template Matching
• ROW-SLAM: Under-Canopy Cornfield Semantic SLAM
• Loop Closure Detection and SLAM in Vineyards with Deep Semantic Cues
• Spatial Acoustic Projection for 3D Imaging Sonar Reconstruction
• Robust Semantic Mapping and Localization on a Free-Flying Robot in Microgravity
• 360VO: Visual Odometry Using a Single 360 Camera
• SAGE: SLAM with Appearance and Geometry Prior for Endoscopy
• Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World
• Continuous-Time vs. Discrete-Time Vision-Based SLAM: A Comparative Study
• DKNAS: A Practical Deep Keypoint Extraction Framework Based on Neural Architecture Search
• Precise 3D Reconstruction of Plants from UAV Imagery Combining Bundle Adjustment and Template Matching
• MSC-VO: Exploiting Manhattan and Structural Constraints for Visual Odometry
• A Model for Multi-View Residual Covariances Based on Perspective Deformation
• Incremental Abstraction in Distributed Probabilistic SLAM Graphs
• UV-SLAM: Unconstrained Line-Based SLAM Using Vanishing Points for Structural Mapping
• A Right Invariant Extended Kalman Filter for Object Based SLAM
• Self-Supervised Ego-Motion Estimation Based on Multi-Layer Fusion of RGB and Inferred Depth
• Visual Localization and Mapping Leveraging the Constraints of Local Ground Manifolds
• Panoptic Multi-TSDFs: A Flexible Representation for Online Multi-Resolution Volumetric Mapping and Long-Term Dynamic Scene Consistency
• FD-SLAM: 3-D Reconstruction Using Features and Dense Matching
• AirDOS: Dynamic SLAM Benefits from Articulated Objects
• A Real-Time Online Learning Framework for Joint 3D Reconstruction and Semantic Segmentation of Indoor Scenes
• Vision-Based Large-Scale 3D Semantic Mapping for Autonomous Driving Applications
• Efficient and Robust Semantic Mapping for Indoor Environments
• Asynchronous Optimisation for Event-Based Visual Odometry
• Optimizing Terrain Mapping and Landing Site Detection for Autonomous UAVs
• Exploration with Global Consistency Using Real-Time Re-Integration and Active Loop Closure
• SO-SLAM: Semantic Object SLAM with Scale Proportional and Symmetrical Texture Constraints
• Accurate and Robust Object-Oriented SLAM with 3D Quadric Landmarks in Outdoors

[top]

Visual-inertial odometry / Visual-inertial SLAM

• High Definition, Inexpensive, Underwater Mapping
• GVINS: Tightly Coupled GNSS-Visual-Inertial Fusion for Smooth and Consistent State Estimation
• AstroLoc: An Efficient and Robust Localizer for a Free-Flying Robot
• VIP-SLAM: An Efficient Tightly-Coupled RGB-D Visual Inertial Planar SLAM
• 1D-LRF Aided Visual-Inertial Odometry for High-Altitude MAV Flight
• Tightly-Coupled Magneto-Visual-Inertial Fusion for Long Term Localization in Indoor Environment
• Interval-Based Visual-Inertial LiDAR SLAM with Anchoring Poses
• The Visual-Inertial-Dynamical Multirotor Dataset
• Map-Based Visual-Inertial Localization: A Numerical Study
• GPS-Denied Global Visual-Inertial Ground Vehicle State Estimation Via Image Registration
• Integrating Point and Line Features for Visual-Inertial Initialization
• Periodic SLAM: Using Cyclic Constraints to Improve the Performance of Visual-Inertial SLAM on Legged Robots
• DM-VIO: Delayed Marginalization Visual-Inertial Odometry
• Constrained Visual-Inertial Localization with Application and Benchmark in Laparoscopic Surgery
• Balancing the Budget: Feature Selection and Tracking for Multi-Camera Visual-Inertial Odometry
• FEJ2: A Consistent Visual-Inertial State Estimator Design
• Decoupled Right Invariant Error States for Consistent Visual-Inertial Navigation
• Leveraging Structural Information to Improve Point Line Visual-Inertial Odometry

[top]

Visual localization / Visual place recognition

• A Deep Feature Aggregation Network for Accurate Indoor Camera Localization
• Learning Visual Localization of a Quadrotor Using Its Noise As Self-Supervision
• Learning Cross-Scale Visual Representations for Real-Time Image Geo-Localization
• Asynchronous Collaborative Localization by Integrating Spatiotemporal Graph Learning with Model-Based Estimation
• Robust Localization of Occluded Targets in Aerial Manipulation Via Range-Only Mapping
• DA-LMR: A Robust Lane Marking Representation for Data Association
• Fusing Convolutional Neural Network and Geometric Constraint for Image-Based Indoor Localization
• Diff-Net: Image Feature Difference Based High-Definition Map Change Detection for Autonomous Driving
• Mobile Robot Localization Considering Uncertainty of Depth Regression From Camera Images
• SemLoc: Accurate and Robust Visual Localization with Semantic and Structural Constraints from Prior Maps
• PixSelect: Less but Reliable Pixels for Accurate and Efficient Localization
• Robust Monocular Localization in Sparse HD Maps Leveraging Multi-Task Uncertainty Estimation
• Keeping an Eye on Things: Deep Learned Features for Long-Term Visual Localization
• OpenSceneVLAD: Appearance Invariant, Open Set Scene Classification
• MultiRes-NetVLAD: Augmenting Place Recognition Training with Low-Resolution Imagery
• LaneMatch: A Practical Real-Time Localization Method Via Lane-Matching
• Binary Graph Descriptor for Robust Relocalization on Heterogeneous Data
• Towards Accurate Loop Closure Detection in Semantic SLAM with 3D Semantic Covisibility Graphs
• HD Ground - a Database for Ground Texture Based Localization
• Crossview Mapping with Graph-Based Geolocalization on City-Scale Street Maps
• Indoor Localization for Quadrotors Using Invisible Projected Tags
• AirLoop: Lifelong Loop Closure Detection
• HD Ground – A Database for Ground Texture Based Localization

[top]

LiDAR odometry / LiDAR SLAM

• Learning Spatiotemporal Occupancy Grid Maps for Lifelong Navigation in Dynamic Scenes
• Reconstruction and Synthesis of Lidar Point Clouds of Spray
• CT-ICP: Real-Time Elastic LiDAR Odometry with Loop Closure
• GCLO: Ground Constrained LiDAR Odometry with Low-Drifts for GPS-Denied Indoor Environments
• Robust Self-Supervised LiDAR Odometry Via Representative Structure Discovery and 3D Inherent Error Modeling
• Direct LiDAR Odometry: Fast Localization with Dense Point Clouds
• Ensemble Kalman Filter Based LiDAR Odometry for Skewed Point Clouds Using Scan Slicing
• LLOL: Low-Latency Odometry for Spinning Lidars
• Performance Guarantees for Spectral Initialization in Rotation Averaging and Pose-Graph SLAM
• ART-SLAM: Accurate Real-Time 6DoF LiDAR SLAM
• Performance Models in Robotics with a Use Case on SLAM
• LT-Mapper: A Modular Framework for LiDAR-Based Lifelong Mapping
• DynamicFilter: An Online Dynamic Objects Removal Framework for Highly Dynamic Environments
• Memory-Efficient Gaussian Fitting for Depth Images in Real Time
• Reconstructing Occluded Elevation Information in Terrain Maps with Self-Supervised Learning

[top]

LiDAR-inertial odometry / LiDAR-inertial SLAM

• Globally Consistent and Tightly Coupled 3D LiDAR Inertial Mapping
• Interval-Based Visual-Inertial LiDAR SLAM with Anchoring Poses
• R3LIVE: A Robust, Real-Time, RGB-Colored, LiDAR-Inertial-Visual Tightly-Coupled State Estimation and Mapping Package
• Graph-based Multi-sensor Fusion for Consistent Localization of Autonomous Construction Robots

[top]

LiDAR localization / LiDAR place recognition

• LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition
• HiTPR: Hierarchical Transformer for Place Recognition in Point Cloud
• FP-Loc: Lightweight and Drift-Free Floor Plan-Assisted LiDAR Localization
• MinkLoc3D-SI: 3D LiDAR Place Recognition with Sparse Convolutions, Spherical Coordinates, and Intensity
• OpenStreetMap-Based LiDAR Global Localization in Urban Environment without a Prior LiDAR Map
• Retriever: Point Cloud Retrieval in Compressed 3D Maps
• RINet: Efficient 3D Lidar-Based Place Recognition Using Rotation Invariant Neural Network

[top]

Point cloud registration

• Translation Invariant Global Estimation of Heading Angle Using Sinogram of LiDAR Point Cloud
• Generalized 3D Rigid Point Set Registration with Anisotropic Positional Error Based on Bayesian Coherent Point Drift
• Fast and Robust Registration of Partially Overlapping Point Clouds
• Deep Bayesian ICP Covariance Estimation
• A Single Correspondence Is Enough: Robust Global Registration to Avoid Degeneracy in Urban Environments
• K-Closest Points and Maximum Clique Pruning for Efficient and Effective 3-D Laser Scan Matching
• FuzzyPSReg: Strategies of Fuzzy Cluster-Based Point Set Registration

[top]

Sensor fusion

• Extrinsic Calibration and Verification of Multiple Non-Overlapping Field of View Lidar Sensors
• LB-L2L-Calib: Accurate and Robust Extrinsic Calibration for Multiple 3D LiDARs with Long Baseline and Large Viewpoint Difference
• Accurate Calibration of Multi-Perspective Cameras from a Generalization of the Hand-Eye Constraint
• LTSR: Long-Term Semantic Relocalization Based on HD Map for Autonomous Vehicles
• HDMapNet: An Online HD Map Construction and Evaluation Framework
• Spatiotemporal Multisensor Calibration Via Gaussian Processes Moving Target Tracking
• Extrinsic Calibration of Multiple Inertial Sensors from In-Flight Data
• Information-Theoretic Online Multi-Camera Extrinsic Calibration
• Self-Supervised Camera Self-Calibration from Video
• FusionNet: Coarse-To-Fine Extrinsic Calibration Network of LiDAR and Camera with Hierarchical Point-Pixel Fusion
• Graph-Based Multi-Sensor Fusion for Consistent Localization of Autonomous Construction Robots

[top]

Inertial odometry

• A2DIO: Attention-Driven Deep Inertial Odometry for Pedestrian Localization Based on 6D IMU
• Improved Kalman-Particle Kernel Filter on Lie Groups Applied to Angles-Only UAV Navigation
• Improved State Propagation through AI-Based Pre-Processing and Down-Sampling of High-Speed Inertial Data

[top]

WiFi SLAM / WiFi Structure-From-Motion

• Single User WiFi Structure from Motion in the Wild
• P2SLAM: Bearing Based WiFi SLAM for Indoor Robots

[top]

Collaborative SLAM

• Robust and Accurate Multi-Agent SLAM with Efficient Communication for Smart Mobiles
• DiSCo-SLAM: Distributed Scan Context-Enabled Multi-Robot LiDAR SLAM with Two-Stage Global-Local Graph Optimization
• Collaborative Robot Mapping Using Spectral Graph Analysis
• MR-GMMapping: Communication Efficient Multi-Robot Mapping System Via Gaussian Mixture Model
• Flexible and Resource-Efficient Multi-Robot Collaborative Visual-Inertial-Range Localization
• A Test Platform for UWB-Based Localization of Dynamic Multi-Agent Systems
• Multirobot Collaborative Monocular SLAM Utilizing Rendezvous
• Self-Supervised Monocular Multi-Robot Relative Localization with Efficient Deep Neural Networks
• Aerial-Ground Robots Collaborative 3D Mapping in GNSS-Denied Environments

[top]

Scene Flow

• RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds
• Scalable Scene Flow from Point Clouds in the Real World
• Fusion-FlowNet: Energy-Efficient Optical Flow Estimation Using Sensor Fusion and Deep Fused Spiking-Analog Network Architectures
• From Scene Flow to Visual Odometry through Local and Global Regularisation in Markov Random Fields
• SAFIT: Segmentation-Aware Scene Flow with Improved Transformer

[top]