Code Monkey home page Code Monkey logo

awesome-object-slam's Introduction

Awesome Object SLAM Awesome

A curated list of Object SLAM papers and resources, inspired by awesome-implicit-representations.

Disclaimer

This list does not aim to be exhaustive. In this list, we consider papers that jointly optimize robot (camera) and object states, where object states typically include object poses and object shape parameters.

For more general SLAM papers, please refer to awesome-visual-SLAM and Awesome-SLAM.

This repo is mainitained by Ziqi Lu and Akash Sharma. You are very welcome to contribute to this repo. If you spot anything wrong or missing, please feel free to submit a pull request or contact the maintainers.

Table of Contents

What is Object SLAM?

Object SLAM, loosely speaking tackles the problem of Simultaneous Localisation and Mapping (SLAM) by building a 3D object-level global environment map from local observations. To build such a map of the environment, object detection, pose estimation and instance segmentation networks are typically used as virtual sensors in a sensor fusion framework. Representing the 3D map with objects is interesting as it is easy to ascribe semantics to the landmarks to perform higher-level tasks such as object manipulation, motion and task planning, etc. It compresses the map by focusing compute and memory for meaningful regions, and map abstraction is also useful for other tasks such as distributed map building.

Papers

Parametric Object Representation (Cubes/Quadrics/6DoF Pose/etc.)

  • 2023

    • An Object SLAM Framework for Association, Mapping, and High-Level Tasks. [PDF]
    • BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects. [PDF] [Code] [Video]
    • Object-based SLAM utilizing unambiguous pose parameters considering general symmetry types. [PDF] [Video]
  • 2022

    • LayoutSLAM: Object Layout based Simultaneous Localization and Mapping for Reducing Object Map Distortion. [PDF]
    • OA-SLAM: Leveraging Objects for Camera Relocalization in Visual SLAM. [PDF] [Code] [Video1] [Video2]
    • SO-SLAM: Semantic Object SLAM with Scale Proportional and Symmetrical Texture Constraints. [PDF] [Code]
    • SQ-SLAM: Monocular Semantic SLAM Based on Superquadric Object Representation. [PDF] [Code]
    • Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation. [PDF] [Code]
  • 2021

    • Accurate and Robust Object-oriented SLAM with 3D Quadric Landmark Construction in Outdoor Environment. [PDF] [Video]
    • A Multi-Hypothesis Approach to Pose Ambiguity in Object-Based SLAM. [PDF] [Video]
    • BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models. [PDF] [Code] [Video]
    • DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM. [PDF]
    • Object-Augmented RGB-D SLAM for Wide-Disparity Relocalisation. [PDF] [Code] [Video]
  • 2020

  • 2019

    • CubeSLAM: Monocular 3D Object SLAM. [PDF] [Code] [Video]
    • Monocular Object and Plane SLAM in Structured Environments. [PDF] [Video]
    • QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in Object-Oriented SLAM. [PDF] [Code] [Video]
    • Real-Time Monocular Object-Model Aware Sparse SLAM. [PDF] [Video]
    • Robust Object-based SLAM for High-Speed Autonomous Navigation. [PDF]
  • 2018

    • Structure Aware SLAM using Quadrics and Planes. [PDF] [Video]
  • 2016

  • 2013

    • SLAM++: Simultaneous Localisation and Mapping at the Level of Objects. [PDF] [Video]
  • 2011

    • Semantic Structure From Motion with Object and Point Interactions. [PDF]
    • Towards Semantic SLAM using a Monocular Camera. [PDF] [Video1] [Video2]
  • 2008

    • Object-based Visual SLAM: How Object Identity Informs Geometry. [PDF]

Field Object Representation (Neural Fields/Dense Grids/etc.)

Inference Methods for Object SLAM

  • 2022

  • 2021

    • Consensus-Informed Optimization Over Mixtures for Ambiguity-Aware Object SLAM. [PDF] [Video]
  • 2020

    • Probabilistic Data Association via Mixture Models for Robust Semantic SLAM. [PDF] [Video]
  • 2019

  • 2018

    • A Unifying View of Geometry, Semantics, and Data Association in SLAM. [PDF] [Video]
  • 2017

    • Probabilistic Data Association for Semantic SLAM. [PDF]
  • 2016

Reviews

  • 2021

    • Advances in Inference and Representation for Simultaneous Localization and Mapping. [PDF]
  • 2020

    • Semantics for Robotic Mapping, Perception and Interaction: A Survey. [PDF]

Resources

Datasets

awesome-object-slam's People

Contributors

520xyxyzq avatar doongli avatar akashsharma02 avatar keevindoherty avatar wenbowen123 avatar guptajakala avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.