2021년 2월 SLAM 뉴스
논문 이름 누르면 자세한 정보가 열립니다!
이번 달 내가 관심가지는 논문들
Tight Integration of Feature-Based Relocalization in Monocular Direct Visual Odometry
- [논문 링크](https://arxiv.org/pdf/2102.01191.pdf) - Daniel Cremers 교수님과 Rui Wang의 연구 - DSO에 relocalization 기능이...?PHASER: A Robust and Correspondence-Free Global Pointcloud Registration
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9327458) - Cadena 교수님, Roland Siegwart 교수님, Juan Nieto 교수님 연구Freetures: Localization in Signed Distance Function Maps
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9327493) - Jeffrey Delmerico, Juan Nieto, Roland Siegwart, Marc Pollefeys, Cesar Cadena Lerma (슬벤저스 ㄷㄷ)Embedding Manifold Structures into Kalman Filters
- [논문 링크](https://arxiv.org/pdf/2102.03804.pdf) - 엄마... 수학 논문...Escaping Poor Local Minima in Large Scale Robust Estimation
- [논문 링크](https://arxiv.org/pdf/2102.10928.pdf)Landmark Based Visual Place Recognition
- [논문 링크](http://www.rsc.wce.ac.in/asset/RSC%202019%20Proceeding.pdf#page=56)Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approaches
- [논문 링크](https://arxiv.org/pdf/2102.05897.pdf)A Switching-Coupled Backend for Simultaneous Localization and Dynamic Object Tracking
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9343683)A Unified Hybrid Formulation for Visual SLAM
- [논문 링크](https://uwspace.uwaterloo.ca/bitstream/handle/10012/16807/Younes_Georges.pdf) - Younes의 PhD 졸업 논문Asynchronous Multi-View SLAM
- [논문 링크](https://arxiv.org/pdf/2101.06562.pdf)Improved Visual Localization via Graph Filtering
- [논문 링크](https://www.mdpi.com/2313-433X/7/2/20/pdf) - Ian Reid 교수님 랩실RigidFusion: RGB-D Scene Reconstruction with Rigidly-moving Objects
- [논문 링크](http://geometry.cs.ucl.ac.uk/projects/2021/rigidfusion/paper_docs/rigidfusion_eg21.pdf) - Niessner 교수님 랩실Review of Place Recognition Approaches: Traditional and Deep Learning Methods
- [논문 링크](https://www.researchgate.net/profile/Melike-Sah/publication/348209290_Review_of_Place_Recognition_Approaches_Traditional_and_Deep_Learning_Methods/links/5ff8579ea6fdccdcb83be2a9/Review-of-Place-Recognition-Approaches-Traditional-and-Deep-Learning-Methods.pdf)Optical flow and scene flow estimation: A survey
- [논문 링크](https://www.sciencedirect.com/science/article/abs/pii/S0031320321000480)Attention Models for Point Clouds in Deep Learning: A Survey
- [논문 링크](https://arxiv.org/pdf/2102.10788.pdf)시간나면 읽어볼 논문들
Automatic object annotation in streamed and remotely explored large 3D reconstructions
- [논문 링크](http://scholar.google.com/scholar_url?url=https://link.springer.com/content/pdf/10.1007/s41095-020-0194-4.pdf&hl=en&sa=X&d=1626110032522529506&ei=chEcYPf1HeaKywSr2qLQBA&scisig=AAGBfm0CNTtgpTwB_3ZlRsv55MN72ZPfzg&nossl=1&oi=scholaralrt&hist=g4sYyGIAAAAJ:9348091814999700012:AAGBfm1H7Xc1GiCUB6yrQDNTUsLvTcDOSA&html=)Characterizing Marginalization and Incremental Operations on the Bayes Tree
- [논문 링크](https://books.google.co.kr/books?hl=en&lr=lang_en&id=uYYbEAAAQBAJ&oi=fnd&pg=PA227&ots=dtdxmozTb2&sig=XFzNCPorAK_8ZqS1-OjVv_jkL60&redir_esc=y#v=onepage&q&f=false) - Kaess, Leonard 교수님Camera Calibration with Pose Guidance
- [논문 링크](https://arxiv.org/pdf/2102.10202.pdf)SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images
- [논문 링크](https://arxiv.org/pdf/2101.07422.pdf)Feature-based Initialization for Monocular Direct Visual Odometry
- [논문 링크](https://vision.in.tum.de/_media/members/demmeln/gladkova2020idp.pdf) - 오... Daniel Cremers 교수님 랩실의 석사 연구?RDS-SLAM: Real-Time Dynamic SLAM Using Semantic Segmentation Methods
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9318990) - Mask-RCNN을 사용해서 움직이는 물체를 검출하고 제거함으로써, 움직이는 물체가 있는 환경에서도 잘 되는 SLAM을 구현. - [지난달에도 RDS-SLAM이라고 나왔는데...](https://ieeexplore.ieee.org/abstract/document/9304693) ㅋㅋㅋ 이름이 겹친다A Collaborative Visual SLAM Framework for Service Robots
- [논문 링크](https://arxiv.org/pdf/2102.03228.pdf)Visual SLAM for robot navigation in healthcare facility
- [논문 링크](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7816967/)The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions
- [논문 링크](https://arxiv.org/pdf/2101.07832.pdf)Practical Globally Optimal Consensus Maximization by Branch-and-Bound based on Interval Arithmetic
- [논문 링크](https://www.sciencedirect.com/science/article/abs/pii/S0031320321000844)Automated building change detection with amodal completion of point clouds
- [논문 링크](https://www.sciencedirect.com/science/article/abs/pii/S0926580521000194)아직 확인 안된 논문들
Online Extrinsic Calibration based on Per-Sensor Ego-Motion Using Dual Quaternions
- [논문 링크](https://arxiv.org/pdf/2101.11440.pdf)Ground-Aware Monocular 3D Object Detection for Autonomous Driving
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9327478)Ego-Motion Estimation Using Recurrent Convolutional Neural Networks through Optical Flow Learning
- [논문 링크](https://search.proquest.com/openview/f62fc1cfdf1b27629d36ccf6736ab5d8/1?pq-origsite=gscholar&cbl=2032404)An adaptive visual Dynamic-SLAM method based on fusing the semantic information
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9323060) - 위에 RDS-SLAM과 비슷한 맥락인 것 같다.PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection
- [논문 링크](https://arxiv.org/pdf/2102.00463.pdf)Unsupervised Learning of Depth and Camera Pose with Feature Map Warping
- [논문 링크](http://scholar.google.com/scholar_url?url=https://www.mdpi.com/1424-8220/21/3/923/pdf&hl=en&sa=X&d=8167159703508464356&ei=W9MeYKnhNoi6mwGNtY2ABA&scisig=AAGBfm1VVxW53aquht0lTVtlImiVy5O2aQ&nossl=1&oi=scholaralrt&hist=g4sYyGIAAAAJ:12090984375177028978:AAGBfm2qKllSiKwPb_W001CAt43ydX5q_Q&html=)Monocular Depth Estimation Using Laplacian Pyramid-Based Depth Residuals
- [논문 링크](https://ieeexplore.ieee.org/document/9316778/)Gated3D: Monocular 3D Object Detection From Temporal Illumination Cues
- [논문 링크](https://arxiv.org/pdf/2102.03602.pdf)Learned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matching
- [논문 링크](https://arxiv.org/pdf/2102.04341.pdf) - 좋은 visual keypoint를 찾는 적절한 camera gain과 exposure를 딥러닝으로 컨트롤! 좋은 연구인것 같다 (하지만 inference 시간이 어떻게 될까...)OV2SLAM : A Fully Online and Versatile Visual SLAM for Real-Time Applications
- [논문 링크](https://arxiv.org/pdf/2102.04060.pdf) -FisheyeDistanceNet++: Self-Supervised Fisheye Distance Estimation with Self-Attention, Robust Loss Function and Camera View Generalization
- [논문 링크](https://www.researchgate.net/profile/Senthil_Yogamani2/publication/348900057_FisheyeDistanceNet_Self-Supervised_Fisheye_Distance_Estimation_with_Self-Attention_Robust_Loss_Function_and_Camera_View_Generalization/links/601524d7a6fdcc071ba15585/FisheyeDistanceNet-Self-Supervised-Fisheye-Distance-Estimation-with-Self-Attention-Robust-Loss-Function-and-Camera-View-Generalization.pdf)SuperVO: A Monocular Visual Odometry based on Learned Feature Matching with GNN
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9342136) - 본격 SuperPoint + SuperGlue의 후계자인척 하기Adversarial Imaging Pipelines
- [논문 링크](https://arxiv.org/pdf/2102.03728.pdf)Points2Vec: Unsupervised Object-level Feature Learning from Point Clouds
- [논문 링크](https://arxiv.org/pdf/2102.04136.pdf) - Roland SiegwartIDOL: Inertial Deep Orientation-Estimation and Localization
- [논문 링크](https://arxiv.org/pdf/2102.04024.pdf)LION: Lidar-Inertial Observability-Aware Navigator for Vision-Denied Environments
- [논문 링크](https://arxiv.org/pdf/2102.03443.pdf) - Luca Carlone 교수님 참여!On the Robustness of Multi-View Rotation Averaging
- [논문 링크](https://arxiv.org/pdf/2102.05454.pdf)DARE-SLAM: Degeneracy-Aware and Resilient Loop Closing in Perceptually-Degraded Environments
- [논문 링크](https://arxiv.org/pdf/2102.05117.pdf)The VCU-RVI Benchmark: Evaluating Visual Inertial Odometry for Indoor Navigation Applications with an RGB-D Camera
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9341713)Speed and Memory Efficient Dense RGB-D SLAM in Dynamic Scenes
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9341542)Nonlinear Observers Design for Vision-Aided Inertial Navigation Systems
- [논문 링크](https://arxiv.org/pdf/2102.05111.pdf)Lightweight 3-D Localization and Mapping for Solid-State LiDAR
- [논문 링크](https://arxiv.org/pdf/2102.03800.pdf)Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning
- [논문 링크](https://arxiv.org/pdf/2102.04960.pdf)Fast and Accurate 3D Object Detection for Lidar-Camera-Based Autonomous Vehicles Using One Shared Voxel-Based Backbone
- [논문 링크](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9340187)Polarimetric Monocular Dense Mapping Using Relative Deep Depth Prior*
- [논문 링크](https://arxiv.org/pdf/2102.05212.pdf)Scale Normalized Image Pyramids with AutoFocus for Object Detection
- [논문 링크](https://arxiv.org/pdf/2102.05646.pdf)Multi-camera fast bundle adjustment algorithm based on normalized matrix dimensionality reduction
- [논문 링크](http://www.irla.cn/en/article/doi/10.3788/IRLA20200156?)Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach
- [논문 링크](https://arxiv.org/pdf/2101.06931.pdf)VIODE: A Simulated Dataset to Address the Challenges of Visual-Inertial Odometry in Dynamic Environments
- [논문 링크](https://arxiv.org/pdf/2102.05965.pdf)A Geometric Nonlinear Stochastic Filter for Simultaneous Localization and Mapping
- [논문 링크](https://arxiv.org/pdf/2102.06150.pdf)VMLoc: Variational Fusion For Learning-Based Multimodal Camera Localization
- [논문 링크](http://www.cs.ox.ac.uk/files/12581/vmloc.pdf)3D-CenterNet: 3D object detection network for point clouds with center estimation priority
- [논문 링크](https://www.sciencedirect.com/science/article/abs/pii/S0031320321000716)HyperPocket: Generative Point Cloud Completion
- [논문 링크](https://arxiv.org/pdf/2102.05973.pdf)Panoramic Visual SLAM Technology for Spherical Images
- [논문 링크](https://www.mdpi.com/1424-8220/21/3/705/pdf)Robust monocular pose tracking of less-distinct objects based on Contour-part model
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9333633)3D mesh transformation preprocessing system in the real space for augmented reality services
- [논문 링크](https://www.sciencedirect.com/science/article/pii/S2405959521000175)A Two-Stage Data Association Approach for 3D Multi-Object Tracking
- [논문 링크](https://arxiv.org/pdf/2101.08684.pdf)Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency
- [논문 링크](https://arxiv.org/pdf/2101.12727.pdf)Single Image Desmoking via Attentive Generative Adversarial Network for Smoke Detection Process
- [논문 링크](https://link.springer.com/article/10.1007/s10694-021-01096-z)Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation
- [논문 링크](https://www.aaai.org/AAAI21Papers/AAAI-2549.XuH.pdf)Deep Inertial Odometry with Accurate IMU Preintegration
- [논문 링크](https://arxiv.org/pdf/2101.07061.pdf)Keypoint detection by wave propagation
- [논문 링크](https://www.spiedigitallibrary.org/journals/journal-of-electronic-imaging/volume-30/issue-1/013003/Keypoint-detection-by-wave-propagation/10.1117/1.JEI.30.1.013003.short?SSO=1)3D reconstruction of deformable objects from RGB-D cameras: an omnidirectional inward-facing multi-camera system
- [논문 링크](http://commandia.unizar.es/wp-content/uploads/VISAPP_2021_222.pdf)Unstructured Road Segmentation Based on Road Boundary Enhancement Point-Cylinder Network Using LiDAR Sensor
- [논문 링크](https://www.mdpi.com/2072-4292/13/3/495/pdf)Decentralised Autonomous Navigation of a UAV Network for Road Traffic Monitoring
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9329129)Semantic Segmentation Leveraging Simultaneous Depth Estimation
- [논문 링크](https://www.mdpi.com/1424-8220/21/3/690/pdf)Text-Guided Graph Neural Networks for Referring 3D Instance Segmentation
- [논문 링크](https://www.aaai.org/AAAI21Papers/AAAI-4433.HuangP.pdf)Robust RGB-D SLAM for Dynamic Environments Based on YOLOv4
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9348738)Visual Odometry/Inertial Integration for Enhanced Land Vehicle Navigation in GNSS Denied Environment
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9348698)LEAD: LiDAR Extender for Autonomous Driving
- [논문 링크](https://arxiv.org/pdf/2102.07989.pdf)OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving
- [논문 링크](https://arxiv.org/pdf/2102.07448.pdf)Point-line-based RGB-D SLAM and Bundle Adjustment Uncertainty Analysis
- [논문 링크](https://arxiv.org/pdf/2102.07110.pdf)Monocular 3D Object Detection using Dual Quadric for Autonomous Driving
- [논문 링크](https://www.sciencedirect.com/science/article/abs/pii/S0925231221002071)FastHand: Fast Hand Pose Estimation From A Monocular Camera
- [논문 링크](https://arxiv.org/pdf/2102.07067.pdf)Mirror Reconstruction
- [논문 링크](https://www.freepatentsonline.com/y2021/0035329.html) - Richard NewcombeSystems and methods for providing a mobile artificial reality user with environmental awareness
- [논문 링크](https://www.freepatentsonline.com/10901215.html) - Richard NewcombeHough2Map – Iterative Event-based Hough Transform for High-Speed Railway Mapping
- [논문 링크](https://arxiv.org/pdf/2102.08145.pdf) - Roland Siegwart, Juan Nieto 교수님 랩실MamboNet: Adversarial Semantic Segmentation for Autonomous Driving
- [논문 링크](https://www.csie.ntu.edu.tw/~fuh/personal/MamboNetAdversarialSemanticSegmentationforAutonomousDriving.pdf)EfficientLPS: Efficient LiDAR Panoptic Segmentation
- [논문 링크](https://arxiv.org/pdf/2102.08009.pdf)Instance Localization for Self-supervised Detection Pretraining
- [논문 링크](https://arxiv.org/pdf/2102.08318.pdf)Linear-PoseNet: A Real-Time Camera Pose Estimation System Using Linear Regression and Principal Component Analysis
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9348762)End-to-End Egospheric Spatial Memory
- [논문 링크](https://arxiv.org/pdf/2102.07764.pdf) - Ronald Clark, Andrew Davison 교수님 랩실 연구PA-MVSNet: Sparse-to-Dense Multi-View Stereo With Pyramid Attention
- [논문 링크](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9352763)Improving Visual Place Recognition Performance by Maximising Complementarity
- [논문 링크](https://arxiv.org/pdf/2102.08416.pdf)Hierarchical Attention Fusion for Geo-Localization
- [논문 링크](https://arxiv.org/pdf/2102.09186.pdf)Intensity-SLAM: Intensity Assisted Localization and Mapping for Large Scale Environment
- [논문 링크](https://arxiv.org/pdf/2102.03798.pdf)Movement Prediction based on Pose Estimation
- [논문 링크](https://netlibrary.aau.at/obvuklhs/content/titleinfo/5809498/full.pdf)Towards Semantic SLAM: 3D Position and Velocity Estimation by Fusing Image Semantic Information with Camera Motion Parameters for Traffic Scene Analysis
- [논문 링크](https://www.researchgate.net/profile/Mostafa-Mansour-2/publication/348716719_remote_sensing_Towards_Semantic_SLAM_3D_Position_and_Velocity_Estimation_by_Fusing_Image_Semantic_Information_with_Camera_Motion_Parameters_for_Traffic_Scene_Analysis/links/600c75fe92851c13fe32078e/remote-sensing-Towards-Semantic-SLAM-3D-Position-and-Velocity-Estimation-by-Fusing-Image-Semantic-Information-with-Camera-Motion-Parameters-for-Traffic-Scene-Analysis.pdf)Consistent Right-Invariant Fixed-Lag Smoother with Application to Visual Inertial SLAM
- [논문 링크](https://arxiv.org/pdf/2102.08596.pdf)Weakly Supervised Learning of Rigid 3D Scene Flow
- [논문 링크](https://arxiv.org/pdf/2102.08945.pdf)Probability Dueling DQN active visual SLAM for autonomous navigation in indoor environmen
- [논문 링크](https://www.emerald.com/insight/content/doi/10.1108/IR-08-2020-0160/full/html)A hybrid global structure from motion method for synchronously estimating global rotations and global translations
- [논문 링크](https://www.sciencedirect.com/science/article/abs/pii/S0924271621000356)D3DLO: Deep 3D LiDAR Odometry
- [논문 링크](https://arxiv.org/pdf/2101.12242.pdf)STEP: Segmenting and Tracking Every Pixel
- [논문 링크](https://arxiv.org/pdf/2102.11859.pdf) - Daniel CremersNew SLAM Fusion Algorithm based on Lidar/IMU Sensors
- [논문 링크](https://www.ion.org/publications/abstract.cfm?articleID=17868)Accurate 3D Localization Using RGB-TOF Camera and IMU for Industrial Mobile Robots
- [논문 링크](https://www.cambridge.org/core/journals/robotica/article/abs/accurate-3d-localization-using-rgbtof-camera-and-imu-for-industrial-mobile-robots/2F4D8821D8BFAA43BF142D27F72BC7E2)Improved Genetic Algorithm for Bundle Adjustment in Photogrammetry
- [논문 링크](https://ieeexplore.ieee.org/abstract/document/9323649)Semantic loop closure detection based on graph matching in multi-objects scenes
- [논문 링크](https://www.sciencedirect.com/science/article/abs/pii/S1047320321000389)Unsupervised Learning of Lidar Features for Use in a Probabilistic Trajectory Estimator
- [논문 링크](https://arxiv.org/pdf/2102.11261.pdf)Accurate Covariance Estimation for Pose Data from Iterative Closest Point Algorithm
- [논문 링크](https://www.ion.org/publications/abstract.cfm?articleID=17866)Related Posts