mlsanityData to 7 Oct 2026

Dynamic Semantic Occupancy Mapping using 3D Scene Flow and Closed-Form Bayesian Inference

arXiv 2108.03180 ↗First posted 6 Aug 2021cs.RO cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

This paper reports on a dynamic semantic mapping framework that incorporates 3D scene flow measurements into a closed-form Bayesian inference model. Existence of dynamic objects in the environment can cause artifacts and traces in current mapping algorithms, leading to an inconsistent map posterior. We leverage state-of-the-art semantic segmentation and 3D flow estimation using deep learning to provide measurements for map inference. We develop a Bayesian model that propagates the scene with flow and infers a 3D continuous (i.e., can be queried at arbitrary resolution) semantic occupancy map outperforming its static counterpart. Extensive experiments using publicly available data sets show that the proposed framework improves over its predecessors and input measurements from deep neural networks consistently.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 51 of its 90 references that are in the map. First posted on arXiv 6 Aug 2021.

Builds on

51 of 90 references.

References · 51

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  4. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  5. 2016End to End Learning for Self-Driving Carscited by 1,000
  6. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  7. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
  8. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 241
  9. 2019Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mappingcited by 181
  10. 2020Predicting Semantic Map Representations from Images using Pyramid Occupancy Networkscited by 175
  11. 20203D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humanscited by 141
  12. 2016SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networkscited by 134
38 more
  1. 2018DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenescited by 130
  2. 2020FLOT: Scene Flow on Point Clouds Guided by Optimal Transportcited by 129
  3. 2020Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentationcited by 112
  4. 2019HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Cloudscited by 108
  5. 2020MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Mapscited by 100
  6. 2021SuMa++: Efficient LiDAR-based Semantic SLAMcited by 100
  7. 2019Just Go with the Flow: Self-Supervised Scene Flow Estimationcited by 98
  8. 2018Fusion++: Volumetric Object-Level SLAMcited by 97
  9. 2020BADGR: An Autonomous Self-Supervised Learning-Based Navigation Systemcited by 97
  10. 2018MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objectscited by 95
  11. 2017Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigationcited by 90
  12. 2018DS-SLAM: A Semantic Visual SLAM towards Dynamic Environmentscited by 90
  13. 2019Volumetric Instance-Aware Semantic Mapping and 3D Object Discoverycited by 79
  14. 2018Learning Navigation Behaviors End-to-End with AutoRLcited by 70
  15. 2018MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAMcited by 65
  16. 2021Semantics for Robotic Mapping, Perception and Interaction: A Surveycited by 56
  17. 2019SegMap: Segment-based mapping and localization using data-driven descriptorscited by 42
  18. 2020Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motioncited by 41
  19. 2019PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Cloudscited by 38
  20. 2019Bayesian Spatial Kernel Smoothing for Scalable Dense Semantic Mappingcited by 34
  21. 2016Meaningful Maps With Object-Oriented Semantic Mappingcited by 31
  22. 2019EM-Fusion: Dynamic Object-Level SLAM with Probabilistic Data Associationcited by 28
  23. 2020Dynamic SLAM: The Need For Speedcited by 24
  24. 2020DeepLiDARFlow: A Deep Learning Architecture For Scene Flow Estimation Using Monocular Camera and Sparse LiDARcited by 24
  25. 2021SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimationcited by 23
  26. 2021MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understandingcited by 22
  27. 2019Robust Dense Mapping for Large-Scale Dynamic Environmentscited by 21
  28. 2017DA-RNN: Semantic Mapping with Data Associated Recurrent Neural Networkscited by 17
  29. 2018Recurrent-OctoMap: Learning State-based Map Refinement for Long-Term Semantic Mapping with 3D-Lidar Datacited by 16
  30. 2021PillarSegNet: Pillar-based Semantic Grid Map Estimation using Sparse LiDAR Datacited by 16
  31. 2017Semantic 3D Occupancy Mapping through Efficient High Order CRFscited by 15
  32. 2015Place Categorization and Semantic Mapping on a Mobile Robotcited by 12
  33. 2020Temporal LiDAR Frame Prediction for Autonomous Drivingcited by 7
  34. 2021Multitask Learning for Scalable and Dense Multilayer Bayesian Map Inferencecited by 7
  35. 2017Gaussian Processes Semantic Map Representationcited by 6
  36. 2018Semantic Mapping with Simultaneous Object Detection and Localizationcited by 4
  37. 2020Inverting the Pose Forecasting Pipeline with SPF2: Sequential Pointcloud Forecasting for Sequential Pose Forecastingcited by 4
  38. 2017Warped Gaussian Processes Occupancy Mapping with Uncertain Inputscited by 3

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 1.

4 papers.

  1. 2022MotionSC: Data Set and Network for Real-Time Semantic Mapping in Dynamic Environmentscited by 40
  2. 2023ConvBKI: Real-Time Probabilistic Semantic Mapping Network with Quantifiable Uncertaintycited by 10
  3. 2022Convolutional Bayesian Kernel Inference for 3D Semantic Mappingcited by 8
  4. 2024Uncertainty-aware Semantic Mapping in Off-road Environments with Dempster-Shafer Theory of Evidencecited by 2