mlsanityData to 14 Oct 2026

RePL: Pseudo-label Refinement for Semi-supervised LiDAR Semantic Segmentation

arXiv 2604.06825 ↗First posted 8 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Semi-supervised learning for LiDAR semantic segmentation often suffers from error propagation and confirmation bias caused by noisy pseudo-labels. To tackle this chronic issue, we introduce RePL, a novel framework that enhances pseudo-label quality by identifying and correcting potential errors in pseudo-labels through masked reconstruction, along with a dedicated training strategy. We also provide a theoretical analysis demonstrating the condition under which the pseudo-label refinement is beneficial, and empirically confirm that the condition is mild and clearly met by RePL. Extensive evaluations on the nuScenes-lidarseg and SemanticKITTI datasets show that RePL improves pseudo-label quality substantially, and in consequence, achieves the state of the art in semi-supervised LiDAR semantic segmentation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 50 references that are in the map. First posted on arXiv 8 Apr 2026.

Builds on

33 of 50 references.

References · 33

  1. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  4. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  5. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
  6. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 463
  7. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 275
  8. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  9. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  10. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 167
  11. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 166
  12. 2019NLNL: Negative Learning for Noisy Labelscited by 151
21 more
  1. 2022Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Datacited by 126
  2. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 125
  3. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 125
  4. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 93
  5. 2021Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 87
  6. 2022Scribble-Supervised LiDAR Semantic Segmentationcited by 69
  7. 2019Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentationcited by 68
  8. 2021Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perceptioncited by 57
  9. 2022Semi-supervised Semantic Segmentation with Error Localization Networkcited by 57
  10. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 54
  11. 2023FRNet: Frustum-Range Networks for Scalable LiDAR Segmentationcited by 50
  12. 2022LESS: Label-Efficient Semantic Segmentation for LiDAR Point Cloudscited by 41
  13. 2023Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentationcited by 33
  14. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 33
  15. 20232D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentationcited by 6
  16. 2023Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentationcited by 6
  17. 2024SegNet4D: Efficient Instance-Aware 4D Semantic Segmentation for LiDAR Point Cloudcited by 5
  18. 2024ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentationcited by 5
  19. 2021Weakly Supervised Pseudo-Label assisted Learning for ALS Point Cloud Semantic Segmentationcited by 3
  20. 2024Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentationcited by 2
  21. 2025LiDAR Based Semantic Perception for Forklifts in Outdoor Environmentscited by 1

Built on by

Not cited yet.