Skip to content

Latest commit

 

History

History
85 lines (58 loc) · 6.82 KB

Paper Survey on Plane SLAM.md

File metadata and controls

85 lines (58 loc) · 6.82 KB

Bibliography on Plane SLAM

Plane Estimation

Year Scene Sensor Method Link
RANSAC 2010 RGBD Indoor Plane detection in point cloud data
Point Cloud Segmentation 2011 RGBD Indoor Clustered, segmented, Classified [a1]
PEAC (AHC) 2014 RGBD Indoor Agglomerative Hierarchical Clustering, Organized Point Cloud [a2]
Conditional Random Field (CRF) 2016 RGBD Indoor Plane Optimization [a3]
Markov Random Field (MRF) 2018 RGBD Indoor Plane Optimization [a4]
PlaneNet 2018 RGB Indoor Depth prediction [a5]
PlaneRecover 2018 RGB Indoor New Plane Structure-Induced Loss [a6]
PlaneRCNN 2019 RGB Indoor Mask, normal [a7]
PlaneRecostruction 2019 RGB Indoor Two stage: plane segmentation + clustering [a8]

Plane-base SLAM

Year Sensor Detection Association Optimization keywords Link
Infinite Planes 2015 RGBD Surface normal Distance and angle Log(qT, q) Homogeneous plane parameter [b1]
Pop-up SLAM 2016 RGB Pop-up from edge Normal, distance and polygon Log(q(Tpi)-1 q(pi)) Pop-up plane model [b2]
Dense piecewise Planar 2017 RGBD RANSAC GIST RANSAC, SIFT, GIST features, Plane [b3]
KDP (Keyframe Dense Plane) 2017 RGBD Region normal Normals, distance, points dist Interactive Projective Plane, local depth map, global planar mapping [b4]
Sparse point + plane 2017 RGBD RANSAC Normals, distance, E = n(x-x0)
Geometric Primitives 2018 RGBD AHC AHC, ORB, Line [b6]
Point + supposed plane 2019 Multi-Plane Normals, distance, points dist F = q(pi)-q(T*pi)
GPM (global plane map) 2020 PEAC Normals, distance E = (Tv1-Tv2) PEAC, ICP tracking, plane-plane match, global plane map (GPM), Fusion reconstruction. [b8]
Points + in-plane points SLAM 2020 RGB RANSAC+ SVD Feature points Normal and in-plane points [b9]
LPVO 2018
OPVO 2019
Structural Regularities 2020

Reference

[a1] Real-Time Plane Segmentation using RGB-D Cameras

[a2] Fast Plane Extraction in Organized Point Clouds Using Agglomerative Hierarchical Clustering

[a3] Real-time 3D Scene Layout from a Single Image Using Convolutional Neural Networks

[a4] Plane-Based Optimization of Geometry and Texture for RGB-D Reconstruction of Indoor Scenes

[a5] PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image

[a6] PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image

[a7] Recovering 3D Planes from a Single Image via Convolutional Neural Networks

[a8] PlaneRecostruction: Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding

Other work on Plane Estimation

  1. Real-Time Plane Segmentation using RGB-D Cameras

[b1] Simultaneous Localization and Mapping with Infinite Planes

[b2] Pop-up SLAM: Semantic Monocular Plane SLAM for Low-texture Environments

[b3] Dense Piecewise Planar RGB-D SLAM for Indoor Environments

[b4] Keyframe-based Dense Planar SLAM (KDP-SLAM)

[b5] Sparse Point-Plane SLAM

[b6] Geometric Primitives Based RGB-D SLAM for Low-texture Environment

[b7] Point-Plane SLAM Using Supposed Planes for Indoor Environments

[b8] Real-time dense 3D reconstruction and camera tracking via embedded planes representation

[b9] From Points to Planes - Adding Planar Constraints to Monocular SLAM Factor Graphs

Other work on Plane-based SLAM

  1. Linear RGB-D SLAM for Planar Environments
  2. Low-Drift Visual Odometry in Structured Environments by Decoupling Rotational and Translational Motion
  3. Visual Odometry with Drift-Free Rotation Estimation Using Indoor Scene Regularities
  4. Multi-planar Monocular Reconstruction of Manhattan Indoor Scenes
  5. RGB-D SLAM Using Point–Plane Constraints for Indoor Environments
  6. From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Clouds
  7. From Points to Planes - Adding Planar Constraints to Monocular SLAM Factor Graphs
  8. RGB-D SLAM with Structural Regularities
  9. VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic Systems