mlsanityData to 7 Oct 2026

Open-world Semantic Segmentation for LIDAR Point Clouds

arXiv 2207.01452 ↗First posted 4 Jul 2022cs.CV cs.ROcited by 29

Not on the map. Why?

Abstract (arXiv)

Current methods for LIDAR semantic segmentation are not robust enough for real-world applications, e.g., autonomous driving, since it is closed-set and static. The closed-set assumption makes the network only able to output labels of trained classes, even for objects never seen before, while a static network cannot update its knowledge base according to what it has seen. Therefore, in this work, we propose the open-world semantic segmentation task for LIDAR point clouds, which aims to 1) identify both old and novel classes using open-set semantic segmentation, and 2) gradually incorporate novel objects into the existing knowledge base using incremental learning without forgetting old classes. For this purpose, we propose a REdundAncy cLassifier (REAL) framework to provide a general architecture for both the open-set semantic segmentation and incremental learning problems. The experimental results show that REAL can simultaneously achieves state-of-the-art performance in the open-set semantic segmentation task on the SemanticKITTI and nuScenes datasets, and alleviate the catastrophic forgetting problem with a large margin during incremental learning.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 30 of its 43 references that are in the map. First posted on arXiv 4 Jul 2022.

Builds on

30 of 43 references.

References · 30

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2016Learning without Forgettingcited by 2,465
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  8. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  9. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  10. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  11. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  12. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
18 more
  1. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  2. 2021Towards Open World Object Detectioncited by 297
  3. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  4. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  5. 2014Towards Open World Recognitioncited by 226
  6. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  7. 2020Modeling the Background for Incremental Learning in Semantic Segmentationcited by 189
  8. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  9. 2018Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Imagescited by 146
  10. 2019Detecting the Unexpected via Image Resynthesiscited by 137
  11. 2021Learning Placeholders for Open-Set Recognitioncited by 121
  12. 2017Encoder Based Lifelong Learningcited by 102
  13. 2020Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentationcited by 96
  14. 2020Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNNcited by 61
  15. 2021Learning Semantic Segmentation of Large-Scale Point Clouds with Random Samplingcited by 51
  16. 2021Deep Metric Learning for Open World Semantic Segmentationcited by 51
  17. 2021Energy-Based Open-World Uncertainty Modeling for Confidence Calibrationcited by 46
  18. 2018PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloudcited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 8; 2024: 8; 2025: 9; 2026: 2.

29 papers.

Sort:

By area:

  1. 2023Open-Vocabulary Point-Cloud Object Detection without 3D Annotationcited by 81
  2. 2024DeFlow: Decoder of Scene Flow Network in Autonomous Drivingcited by 29
  3. 2023OpenSight: A Simple Open-Vocabulary Framework for LiDAR-Based Object Detectioncited by 22
  4. 2023Novel Class Discovery for 3D Point Cloud Semantic Segmentationcited by 21
  5. 2023A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Applicationcited by 21
  6. 2024AnoVox: A Benchmark for Multimodal Anomaly Detection in Autonomous Drivingcited by 14
  7. 20243D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillationcited by 13
  8. 2024An Empirical Study of Training State-of-the-Art LiDAR Segmentation Modelscited by 12
  9. 2022PointCaM: Cut-and-Mix for Open-Set Point Cloud Learningcited by 11
  10. 2024Revisiting Out-of-Distribution Detection in LiDAR-based 3D Object Detectioncited by 11
  11. 2022Segmenting Known Objects and Unseen Unknowns without Prior Knowledgecited by 9
  12. 2023Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Datacited by 9
17 more
  1. 2024Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Datacited by 8
  2. 2025Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentationcited by 8
  3. 20233D Indoor Instance Segmentation in an Open-Worldcited by 7
  4. 2024Lidar Panoptic Segmentation in an Open Worldcited by 7
  5. 2025Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learningcited by 5
  6. 2023Novel class discovery meets foundation models for 3D semantic segmentationcited by 4
  7. 2024PDF: A Probability-Driven Framework for Open World 3D Point Cloud Semantic Segmentationcited by 4
  8. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  9. 2025Towards 3D Objectness Learning in an Open Worldcited by 2
  10. 2025Relative Energy Learning for LiDAR Out-of-Distribution Detectioncited by 2
  11. 2023Point Cloud Video Anomaly Detection Based on Point Spatio-Temporal Auto-Encodercited by 1
  12. 2025A Novel Decomposed Feature-Oriented Framework for Open-Set Semantic Segmentation on LiDAR Datacited by 1
  13. 2025Finding Outliers in a Haystack: Anomaly Detection for Large Pointcloud Scenescited by 1
  14. 2026Depth-Only Open-Vocabulary 3D Semantic Segmentation For Privacy-Preserving Robotic Applicationscited by 1
  15. 2025Open-world Point Cloud Semantic Segmentation: A Human-in-the-loop Frameworkcited by 0
  16. 2025UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Vehiclescited by 0
  17. 2026Neural Distribution Prior for LiDAR Out-of-Distribution Detectioncited by 0