mlsanityData to 7 Oct 2026

A Review on Visual-SLAM: Advancements from Geometric Modelling to Learning-based Semantic Scene Understanding

arXiv 2209.05222 ↗First posted 12 Sep 2022cs.RO cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Simultaneous Localisation and Mapping (SLAM) is one of the fundamental problems in autonomous mobile robots where a robot needs to reconstruct a previously unseen environment while simultaneously localising itself with respect to the map. In particular, Visual-SLAM uses various sensors from the mobile robot for collecting and sensing a representation of the map. Traditionally, geometric model-based techniques were used to tackle the SLAM problem, which tends to be error-prone under challenging environments. Recent advancements in computer vision, such as deep learning techniques, have provided a data-driven approach to tackle the Visual-SLAM problem. This review summarises recent advancements in the Visual-SLAM domain using various learning-based methods. We begin by providing a concise overview of the geometric model-based approaches, followed by technical reviews on the current paradigms in SLAM. Then, we present the various learning-based approaches to collecting sensory inputs from mobile robots and performing scene understanding. The current paradigms in deep-learning-based semantic understanding are discussed and placed under the context of Visual-SLAM. Finally, we discuss challenges and further opportunities in the direction of learning-based approaches in Visual-SLAM.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 37 of its 111 references that are in the map. First posted on arXiv 12 Sep 2022.

Builds on

37 of 111 references.

References · 37

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  3. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  4. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
  5. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  6. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  7. 2016Direct Sparse Odometrycited by 479
  8. 2017VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimatorcited by 418
  9. 20193D Scene Graph: A Structure for Unified Semantics, 3D Space, and Cameracited by 280
  10. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
  11. 2015Conditional Random Fields as Recurrent Neural Networkscited by 213
  12. 2020Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructionscited by 205
25 more
  1. 2015ParseNet: Looking Wider to See Bettercited by 176
  2. 2017DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networkscited by 173
  3. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  4. 2017CNN-SLAM: Real-time dense monocular SLAM with learned depth predictioncited by 152
  5. 2018CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAMcited by 151
  6. 2021Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphscited by 144
  7. 2016SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networkscited by 134
  8. 2021SuMa++: Efficient LiDAR-based Semantic SLAMcited by 100
  9. 2017VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problemcited by 51
  10. 2016SE3-Nets: Learning Rigid Body Motion using Deep Neural Networkscited by 48
  11. 2017Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Camerascited by 45
  12. 2020DOPS: Learning to Detect 3D Objects and Predict their 3D Shapescited by 27
  13. 2019Direct Sparse Mappingcited by 25
  14. 2021SO-SLAM: Semantic Object SLAM with Scale Proportional and Symmetrical Texture Constraintscited by 19
  15. 2017Pop-up SLAM: Semantic Monocular Plane SLAM for Low-texture Environmentscited by 17
  16. 2020CamVox: A Low-cost and Accurate Lidar-assisted Visual SLAM Systemcited by 14
  17. 2021From SLAM to Situational Awareness: Challenges and Surveycited by 14
  18. 2020A Real-Time Approach for Chance-Constrained Motion Planning with Dynamic Obstaclescited by 9
  19. 2018Balancing Global Exploration and Local-connectivity Exploitation with Rapidly-exploring Random disjointed-Treescited by 8
  20. 2019Bayesian Local Sampling-based Planningcited by 7
  21. 2021S3LAM: Structured Scene SLAMcited by 5
  22. 2017Towards Visual Ego-motion Learning in Robotscited by 4
  23. 2017Dense RGB-D semantic mapping with Pixel-Voxel neural networkcited by 4
  24. 2017Endo-VMFuseNet: Deep Visual-Magnetic Sensor Fusion Approach for Uncalibrated, Unsynchronized and Asymmetric Endoscopic Capsule Robot Localization Datacited by 2
  25. 2017EndoSensorFusion: Particle Filtering-Based Multi-sensory Data Fusion with Switching State-Space Model for Endoscopic Capsule Robotscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 1; 2025: 2; 2026: 2.

8 papers.

  1. 2023Psy-LLM: Scaling up Global Mental Health Psychological Services with AI-based Large Language Modelscited by 36
  2. 2024LiDAR-Guided Cross-Attention Fusion for Hyperspectral Band Selection and Image Classificationcited by 11
  3. 2023Real-time Aerial Detection and Reasoning on Embedded-UAVscited by 3
  4. 2023An Overview about Emerging Technologies of Autonomous Drivingcited by 2
  5. 2026VEOcc: Voxel-Centric Online Semantic Occupancy Prediction For Embodied Scene Understandingcited by 1
  6. 2025Spatial Reasoner: A 3D Inference Pipeline for XR Applicationscited by 0
  7. 2025Deep Learning Perspective of Scene Understanding in Autonomous Robotscited by 0
  8. 2026A Review Of Robotic World Models For Dynamic Environments Based On Factor And Scene Graphscited by 0