Skip to content

Latest commit

 

History

History
60 lines (41 loc) · 2.7 KB

AutoLabeling.md

File metadata and controls

60 lines (41 loc) · 2.7 KB

Techniques Used in AutoLabeling Project

This repository provides an up-to-date list of techniques used for autolabeling project.

=============================

Table of contents

  1. 3D Reconstruction Techniques
    1.1 SLAM Techniques
    1.2 Structure from Motion
  2. Instance and Semantic Segmentation
    2.1 Datasets
    2.2 Instance Segmentation
    2.3 Semantic Segmentation
    2.4 Video-based Approaches
  3. Online/Offline HD Map Construction
    3.1 Lane-based SLAM
    3.2 Lane marks Detection
    3.3 Road Reconstruction
    4.3 Road Change Detection

1. 3D Reconstruction Techniques

1.1 SLAM Techniques

  • VILENS: Visual, Inertial, Lidar, and Leg Odometry for All-Terrain Legged Robots; [Paper] [Project]
  • 无人车业务中的视觉三维重建 [Website]

1.2 Structure from Motion

  • COLMAP; [Project]
  • openMVG; [Project]
  • Awesome 3D reconstruction list; [Website]
  • OpenSfM; [Website]
  • CMVS-PMVS; [Website]
  • Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award); [Website]
  • Divide and Conquer: Efficient Large-Scale Structure from Motion Using Graph Partitioning [Paper]

2 Instance and Semantic Segmentation

2.1 Datasets

2.2 Instance Segmentation

2.3 Semantic Segmentation

2.4 Video-based Approaches

3 Instance and Semantic Segmentation

3.1 Lane-based SLAM

3.2 Lane marks Detection

3.3 Road Reconstruction

3.4 Road Change Detection