mlsanityData to 7 Oct 2026

360^circ from a Single Camera: A Few-Shot Approach for LiDAR Segmentation

arXiv 2309.06197 ↗First posted 12 Sep 2023cs.CV cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

Deep learning applications on LiDAR data suffer from a strong domain gap when applied to different sensors or tasks. In order for these methods to obtain similar accuracy on different data in comparison to values reported on public benchmarks, a large scale annotated dataset is necessary. However, in practical applications labeled data is costly and time consuming to obtain. Such factors have triggered various research in label-efficient methods, but a large gap remains to their fully-supervised counterparts. Thus, we propose ImageTo360, an effective and streamlined few-shot approach to label-efficient LiDAR segmentation. Our method utilizes an image teacher network to generate semantic predictions for LiDAR data within a single camera view. The teacher is used to pretrain the LiDAR segmentation student network, prior to optional fine-tuning on 360^circ data. Our method is implemented in a modular manner on the point level and as such is generalizable to different architectures. We improve over the current state-of-the-art results for label-efficient methods and even surpass some traditional fully-supervised segmentation networks.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 53 of its 65 references that are in the map. First posted on arXiv 12 Sep 2023.

Builds on

53 of 65 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  6. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  7. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  8. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  9. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  10. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  11. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  12. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
38 more
  1. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  2. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  3. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  4. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  5. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  6. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  7. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  8. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  9. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 222
  10. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  11. 2020A2D2: Audi Autonomous Driving Datasetcited by 189
  12. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  13. 2023CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPcited by 178
  14. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  15. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  16. 2019xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 129
  17. 2022Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Datacited by 126
  18. 2022Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentationcited by 118
  19. 2020Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Cloudscited by 116
  20. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 92
  21. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  22. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  23. 2022Scribble-Supervised LiDAR Semantic Segmentationcited by 69
  24. 2022Debiased Self-Training for Semi-Supervised Learningcited by 62
  25. 2021Learning 3D Semantic Segmentation with only 2D Image Supervisioncited by 60
  26. 20203D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentationcited by 58
  27. 2022CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentationcited by 54
  28. 2021ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentationcited by 52
  29. 2021A Survey on Deep Domain Adaptation for LiDAR Perceptioncited by 46
  30. 2021Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentationcited by 46
  31. 2022GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentationcited by 35
  32. 2023Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Losscited by 35
  33. 2021Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapterscited by 21
  34. 2019LATTE: Accelerating LiDAR Point Cloud Annotation via Sensor Fusion, One-Click Annotation, and Trackingcited by 19
  35. 2022LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentationcited by 16
  36. 2022Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learningcited by 15
  37. 2021SALT: A Semi-automatic Labeling Tool for RGB-D Video Sequencescited by 10
  38. 2021PDC: Piecewise Depth Completion utilizing Superpixelscited by 5

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 5; 2026: 1.

12 papers.

  1. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 53
  2. 2023FRNet: Frustum-Range Networks for Scalable LiDAR Segmentationcited by 50
  3. 2024RadarPillars: Efficient Object Detection from 4D Radar Point Cloudscited by 23
  4. 2025LeAP: Consistent multi-domain 3D labeling using Foundation Modelscited by 8
  5. 2024ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentationcited by 5
  6. 2024Text3DAug -- Prompted Instance Augmentation for LiDAR Perceptioncited by 4
  7. 2025Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systemscited by 4
  8. 2025HiLoTs: High-Low Temporal Sensitive Representation Learning for Semi-Supervised LiDAR Segmentation in Autonomous Drivingcited by 3
  9. 2024Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentationcited by 2
  10. 2025Classifier Ensemble for Efficient Uncertainty Calibration of Deep Neural Networks for Image Classificationcited by 1
  11. 2025D-PLS: Decoupled Semantic Segmentation for 4D-Panoptic-LiDAR-Segmentationcited by 0
  12. 2026GridNet-HD: A High-Resolution Multi-Modal Dataset for LiDAR-Image Fusion on Power Line Infrastructurecited by 0