Roadmaps

A good roadmap

Papers and codes

Monocular SLAM

RGB

DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras Paper Code

TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo Paper Code Project page

Dynamic Dense RGB-D SLAM using Learning-based Visual Odometry Paper Code

An Overview on Visual SLAM: From Tradition to Semantic Paper

DynaVINS: A Visual-Inertial SLAM for Dynamic Environments Paper Code

Deep Depth Estimation from Visual-Inertial SLAM Paper Code

DeepFactors: Real-Time Probabilistic Dense Monocular SLAM Paper Code

VOLDOR-SLAM: For the Times When Feature-Based or Direct Methods Are Not Good Enough Paper Code

RAFT: Recurrent All Pairs Field Transforms for Optical Flow Paper Code

DeepV2D: Video to Depth with Differentiable Structure from Motion Paper Code

DeepTAM: Deep Tracking and Mapping Paper Code Project page

CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM Paper Code

RGB and camera poses

SimpleRecon: 3D Reconstruction Without 3D Convolutions Paper Code

NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video Paper Code Project page

Atlas: End-to-End 3D Scene Reconstruction from Posed Images Paper Code

RGB-D SLAM

iMAP Implicit Mapping and Positioning in Real-Time Paper Code Project page

Books

slambook-en

Computer Vision: Algorithms and Applications

Multiple View Geometry in Computer Vision Second Edition

Lectures

Cyrill Stachniss Lectures

Tartan SLAM Series

3D Computer Vision - NUS

Youtube Videos

The Basics about Bundle Adjustment

Feature-based, Direct, and Deep Learning Methods of Visual Odometry

Daniel Cremers | Deep and Direct Visual SLAM | Tartan SLAM Series

TUM Playlist

Courses

SLAM course by Cyrill Stachniss

Autonomous Navigation for Flying Robots

Visual Perception for Self-Driving Cars

3D Reconstruction - Multiple Viewpoints

NUS - 3D Computer Vision

Labs and Groups

Computer Vision Group TUM Home

The Dyson Robotics Lab at Imperial College Home

Computer Vision and Geometry Group Home

StachnissLab-Photogrammetry & Robotics Home

Blogs

SLAM

Mathworks

Pinhole camera model

What are Intrinsic and Extrinsic Camera Parameters in Computer Vision?

Image Formation and Pinhole Model of the Camera

From depth map to point cloud

Dissecting the Camera Matrix, Part 3: The Intrinsic Matrix

Estimate Point Clouds From Depth Images in Python

Depth estimation

Depth Estimation: Basics and Intuition

People and Channels

Cyrill Stachniss

First Principles of Computer Vision