[슬램슬램합니다] Visual SLAM의 Past, Present and Future!

https://youtu.be/eoLJMNJnTUg

@0:00 - 소개

@8:38 - Local Features

@1:16:09 - Feature-based SLAM

@1:59:37 - Direct SLAM

@2:44:40 - Visual-Inertial SLAM

@3:58:10 - SLAM with Deep Learning

 

1. Feature Detection:

Moravec, Harris corner, FAST corner, SIFT, BRIEF, FLANN, LSH, Multi-probe LSH, ORB, AKAZE

 

2. Feature-based SLAM:

Mono-SLAM, PTAM, ORB-SLAM, Pro SLAM

 

3. Direct SLAM:

DTAM, LSD-SLAM, SVO, SVO 2.0, DSO

 

4. Visual-Inertial SLAM:

MSCKF, IMU Preintegration, OKVIS, ROVIO, Maplab, VINS-Mono, VINS-Fusion

 

5. SLAM with Deep Learning:

CNN-SLAM, SuperPoint, LIFT, PoseNet, UnDeepVO, CubeSLAM, DeepFactors, DSAC