Skip to content

Latest commit

 

History

History
349 lines (254 loc) · 39.8 KB

SLAM_Research_2018.md

File metadata and controls

349 lines (254 loc) · 39.8 KB

Recent_SLAM_Research

【回馈社区】跟踪SLAM前沿动态 (2018),技术更新太快,开启paper暴走模式,精选paper包括纯视觉SLAM,三维重建,基础数学工具,导航路径规划,深度学习SLAM,激光与视觉融合等类别。

SLAM 能力图

战斗吧

Visual SLAM

115. 2018-12-18-Image-based Navigation using Visual Features and MapETH formulate the map construction and self-localizationproblems as convex quadratic and second-order cone programs,respectively

114. 2018-12-18-From Coarse to Fine: Robust Hierarchical Localization at Large Scale HF-Net, a hierarchical localization approach based on a monolithic CNN that simultaneously predicts local features and global descriptors foraccurate 6-DoF localization

105. 2018-12-07-Depth from Motion for Smartphone AR google 单目深度估计,效果很好

104. 2018-12-06-Stereo Visual-Inertial SLAM With Points and Lines 双目IMU加点线

98. 2018-11-18-DynaSLAM: Tracking, Mapping and Inpainting in Dynamic ScenesFCN 辅助动态场景SLAM,代码

95. 2018-11-16-RGB-D SLAM in Dynamic Environments Using Points Correlations 解决动态物体影响

89. 2018-11-06-Non-iterative RGB-D-inertial odometry轻量型融合

88. 2018-11-06-Dense RGB-D-Inertial SLAM with Map Deformations RGBD 与IMU融合

87. 2018-11-06-Autonomous flight with robust visual odometry under dynamic lighting conditions很少见到韩国人做的SLAM,好像基本不开源,这个光照鲁棒性方法就无从验证了。

76. 2018-10-15-Analysis of the Impact of Field of View on WideAngle Cameras in SLAM 一篇分析视场角对SLAM影响的硕士论文

74. 2018-10-11-SE(2)-Constrained Visual Inertial Fusion for Ground Vehicles 贡献:This paper proposed a new visual inertial fusion framework for ground vehicles, based on an SE(2)-constrained pose parameterization.

73. 2018-10-11-A Structureless Approach for Visual Odometry 三点改进: 1) the complexity of our solution is lower than those of the state-of-the-art methods, 2) no extra matrix operations required to eliminate map points, 3) no need guesses on map points’ initial locations.

68. 2018-09-26-Linear SLAM: Linearising the SLAM Problems using Submap Joining 创建大地图,有代码在openslam上,但是没找到

67. 2018-09-26-Gaze Selection for Enhanced Visual Odometry During Navigation 控制机器人“眼球”看向特征点多的地方

63. 2018-09-17-Efficient 2D-3D Matching for Multi-Camera Visual Localization 已有地图时,做定位.

62. 2018-09-17-DSVO: Direct Stereo Visual Odometry没有双目的matching,另一个摄像头的作用是优化尺度,代码在此.

59. [CVPR 2018] Polarimetric Dense Monocular SLAM 偏振光传感器SLAM,传感器原理

54. [CVPR 2018] Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions 针对于场景变化较大时,例如四季变换的SLAM数据集

53. [ICRA 2018] Online Initialization and Automatic Camera-IMU Extrinsic Calibration for Monocular Visual-Inertial SLAM 单目IMU自动标定,老铁知道比VINS好在哪里么

51. [ICRA 2018] Assigning Visual Words to Places for Loop Closure Detection 使用GNG clustering algorithm

48. [ICRA 2018] Feature-constrained Active Visual SLAM for Mobile Robot Navigation路径规划时候考虑特征点数量,代码在此

45. [ICRA 2018] Detection and Resolution of Motion Conflict in Visual Inertial Odometry 解决视觉与IMU估计值之间冲突问题

----------ECCV 2018【都无代码,可惜】----------

44. 2018-09-14-Realtime Time Synchronized Event-based Stereo 双目事件相机,第一家吧

43. 2018-09-14-Stereo relative pose from line and point feature triplets 点线结合,但是匹配的是三帧图像

40. 2018-09-14-Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Driving 沈老师出品,既估计相机位姿,也估计物体位置,对动态物体鲁棒

38. 2018-09-14-Semantically Aware Urban 3D Reconstruction with Plane-Based Regularization 最近都很喜欢加平面信息做SLAM

37. 2018-09-14-VSO: Visual Semantic Odometry 题目越短,文章越牛逼?

36. 2018-09-14-Direct Sparse Odometry with Rolling Shutter 同样是Cremers出品,看题目就知道了

35. 2018-09-14-Modeling Varying Camera-IMU Time Offset in Optimization-Based Visual-Inertial Odometry 科大沈老师门生根叔出品,解决了卷帘快门问题,加速IMU预积分,以及使初始化更鲁棒,AR界梦寐以求的算法,可惜没代码

33. 2018-09-14-Good Line Cutting: towards Accurate Pose Tracking of Line-assisted VO/VSLAM 对于线特征提取线内信息最多的一段做SLAM,声称对低纹理,运动模糊鲁棒

32. 2018-09-14-Linear RGB-D SLAM for Planar Environments 卡尔曼滤波估计位姿与平面特征

----------ECCV 2018 ----------

31. 2018-09-10-Monocular Object and Plane SLAM in Structured Environments. 约束中加入识别的物体与平面

30. DOVO: Mixed Visual Odometry Based on Direct Method and Orb Feature: 通过特征点个数判断用直接法与光流法。交替使用

29. UFSM_VO: STEREO ODOMETRY BASED ON UNIFORMLY FEATURE SELECTION AND STRICTLY CORRESPONDENCE MATCHING: 创新度一般

28. A Review of Visual-Inertial Simultaneous Localization and Mapping from Filtering-Based and Optimization-Based Perspectives: VINSLAM 综述

27. A Loop Closure Detection Algorithm in Dynamic Scene: 动态环境下回环检测

26. Directional grid maps: modeling multimodal angular uncertainty in dynamic environments

25. Grid Map Guided Indoor 3D Reconstruction for Mobile Robots with RGB-D Sensors

24. Robustness Improvement of Long Range Landmark Tracking for Mobile Robots

23. Lightweight Visual Odometry for Autonomous Mobile Robots

22. Enhanced Visual Loop Closing for Laser-Based SLAM

21. A Fast Stereo Visual-Inertial Odometry for MAVs

20. Low-Cost Multiple-MAV SLAM Using Open Source Software

19. PCR-Pro: 3D Sparse and Different Scale Point Clouds Registration and Robust Estimation of Information Matrix For Pose Graph SLAM https://sites.google.com/view/pcr-pro

18. Comparison of two different objective functions in 2D point feature SLAM

17. Pose Estimation with Dual Quaternions and Iterative Closest Point

16. SLAMBench2: Multi-Objective Head-to-Head Benchmarking for Visual SLAM https://github.com/pamela-project/slambench2

15. Estimating Metric Poses of Dynamic Objects Using Monocular Visual-Inertial Fusion

14. Data-Efficient Decentralized Visual SLAM https://github.com/uzh-rpg/dslam_open

13. Direct Sparse Visual-Inertial Odometry using Dynamic Marginalization

12. A General Framework for Flexible Multi-Cue Photometric Point Cloud Registration : https://gitlab.com/srrg-software/srrg_mpr

10. DS-PTAM: Distributed Stereo Parallel Tracking and Mapping SLAM System

9. A Robust and Accurate Simultaneous Localization and Mapping System for RGB-D Cameras

8. Online Photometric Calibration of Auto Exposure Video for Realtime Visual Odometry and SLAM (对于光照变化很鲁棒)

7. Direct Sparse Odometry with Rolling Shutter

6. Online Temporal Calibration for Monocular Visual-Inertial Systems

5. PL-VIO: Tightly-Coupled Monocular Visual–Inertial Odometry Using Point and Line Features

4. Gaoxiang: LDSO: Direct Sparse Odometry with Loop Closure 带有回环检测的DSO

3. MULTICOL-SLAM - A MODULAR REAL-TIME MULTI-CAMERA SLAM SYSTEM

2. Loosely-Coupled Semi-Direct Monocular SLAM

1. Absolute Orientation and Localization Estimation from an Omnidirectional Image

路径规划导航

12. 2018-12-30-Robust Path Planning Against Pose Errors for Mobile Robots in Rough Terrain 机器人位姿有误差时候规划路径

基础工具 Basic tools

29. 2018-12-30-Calibration of Heterogeneous Sensor Systems 各种传感器之间标定

27. 2018-12-27-Impact of light on augmented reality 光照对AR影响

26. 2018-12-20-An Extrinsic Calibration Method for Binocular Cameras and Swing 2D Laser Rangefinder 相机与旋转2D激光标定

24. 2018-12-07-Two-pass K Nearest Neighbor Search for Feature Tracking 增强的KNN特征匹配方法

22. 2018-11-22-A FAST-BRISK Feature Detector with Depth Information 融合深度的特征点提取方法

19. 2018-10-20-Accurate Sparse Feature Regression Forest Learning for Real-Time Camera Relocalization 机器学习与特征点的混合方法做重定位

18. 2018-10-20-Four- and Seven-Point Relative Camera Pose from Oriented Features 利用特征点方向信息计算相对位姿

16. 2018-10-08-A Tutorial on Quantitative Trajectory Evaluationfor Visual(-Inertial) Odometry SLAM 误差专门评测方法,终于有大佬说清楚了。代码在此

14. 2018-09-25-A Versatile Method for Depth Data Error Estimation in RGB-D Sensors 判断RGBD深度信息准确性的方法

11. An Improved RANSAC Algorithm for Simultaneous Localization and Mapping

10. Baidu Apollo Auto-Calibration System - An Industry-Level Data-Driven and Learning based Vehicle Longitude Dynamic Calibrating Algorithm

9.RES-Q: Robust Outlier Detection Algorithm for Fundamental Matrix Estimation

8.Fast and robust local feature extraction for 3D reconstruction

7.Matrix Difference in Pose-Graph Optimization https://gitlab.com/srrg-software/srrg_g2o_chordal_plugin

6. Nonlinear Distortion Calibration of an Optical Flow Sensor for Monocular Visual Odometry

5. Five-point algorithm: an efficient cloud-based FPGA implementation

4. SC-RANSAC: Spatial consistency on RANSAC

3.Towards A Deep Insight into Landmark-based Visual Place Recognition: Methodology and Practice

2. In Defense of Relative Multi-View Geometry

1. MatchBench: An Evaluation of Feature Matchers

视觉激光融合 Fusion of visual and laser

3. Laser-visual-inertial odometry and mapping with high robustness and low drift1

2. ROBUST LOOP CLOSURES FOR SCENE RECONSTRUCTION BY COMBINING ODOMETRY AND VISUAL CORRESPONDENCES (RGBD+odometry 做回环检测)https://www.youtube.com/watch?v=peXrP374MVI https://github.com/zlaskar/Robust-Loop-Closures

1.Scale Correct Monocular Visual Odometry Using a LiDAR Altimeter

三维重建 3D reconstruction

7.2018-09-17-Building Dense Reflectance Maps of Indoor Environments using an RGB-D Camera 去除光源条件对重建的影响.

6.2018-09-15-Real-time High-accuracy Three-Dimensional Reconstruction with Consumer RGB-D Cameras加入了uncertaintyaware,and local-to-global RGB-D bundle adjustment strategy

5.Object Pose Estimation from Monocular Image using Multi-View Keypoint Correspondence

4.Depth Super-Resolution Meets Uncalibrated Photometric Stereo (低分辨率depth+不同光照下,同一视角高分辨率RBG => 高分辨率深度图)

3. Robust 3D Surface Reconstruction in Real-Time with Localization Sensor

2. EchoFusion: Tracking and Reconstruction of Objects in 4D Freehand Ultrasound Imaging without External Trackers

1. PSDF Fusion: Probabilistic Signed Distance Function for On-the-fly 3D Data Fusion and Scene Reconstruction

深度学习(DL)+SLAM

37. 2018-12-28-MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM分割出动态物体 ,Andrew Davison

36. 2018-12-28-SfMLearner++: Learning Monocular Depth & Ego-Motion using Meaningful Geometric Constraints sfmLearner加强版,加入了对极约束,减少参数和模型大小

34. 2018-12-18-Self-Improving Visual Odometry magic leap出品,可以线上训练网络,自我提升vo性能,厉害了!

31. 2018-12-06-Matching Features without Descriptors: Implicitly Matched Interest Points (IMIPs)Davide Scaramuzza Michael Bloesch 发表不需要描述子使用CNN就能匹配特征点方法

30. 2018-12-06-DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds利用深度学习做激光点云匹配

23. 2018-10-19-Scene Coordinate Regression with Angle-Based Reprojection Loss for Camera Relocalization同下,合在一起读,可以加强理解

22. 2018-10-19-DSAC - Differentiable RANSAC for Camera Localization 深度学习重定位,代码

19. 2018-10-15-Learning to Solve Nonlinear Least Squares for Dense Tracking and Mapping Andrew J. Davison 的 learned optimizer

8. 2018-07-25 Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry.TUM DL+DSO大作

7. Fusion++: Volumetric Object-Level SLAM

6. UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning github:https://github.com/drmaj/UnDeepVO

5. Learning-based Image Enhancement for Visual Odometry in Challenging HDR Environments

4. Graph-Based Place Recognition in Image Sequences with CNN Features

3. VSO: Visual Semantic Odometry

2. Real-time Dense Monocular SLAM with Online Adapted Depth Prediction Network

1. DeepTAM: Deep Tracking and Mapping