mlsanityData to 7 Oct 2026

Rethinking Range View Representation for LiDAR Segmentation

arXiv 2303.05367 ↗First posted 9 Mar 2023cs.CV cs.ROcited by 126

On the map: World models → World modeling from LiDAR generation

Abstract (arXiv)

LiDAR segmentation is crucial for autonomous driving perception. Recent trends favor point- or voxel-based methods as they often yield better performance than the traditional range view representation. In this work, we unveil several key factors in building powerful range view models. We observe that the "many-to-one" mapping, semantic incoherence, and shape deformation are possible impediments against effective learning from range view projections. We present RangeFormer -- a full-cycle framework comprising novel designs across network architecture, data augmentation, and post-processing -- that better handles the learning and processing of LiDAR point clouds from the range view. We further introduce a Scalable Training from Range view (STR) strategy that trains on arbitrary low-resolution 2D range images, while still maintaining satisfactory 3D segmentation accuracy. We show that, for the first time, a range view method is able to surpass the point, voxel, and multi-view fusion counterparts in the competing LiDAR semantic and panoptic segmentation benchmarks, i.e., SemanticKITTI, nuScenes, and ScribbleKITTI.

Key facts. Cited by 126 papers in the map (data through 7 Oct 2026). Placed in World modeling from LiDAR generation, one of 11 directions in World models. Builds on 76 of its 93 references that are in the map. First posted on arXiv 9 Mar 2023.

Builds on

76 of 93 references.

Closest ancestors · 2

Same direction, newest first

  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space7 Jun
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2 Dec

Other references · 74

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  8. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  10. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  11. 2018YOLOv3: An Incremental Improvementcited by 2,652
  12. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
38 more
  1. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  2. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  3. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  4. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  5. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  6. 2018Panoptic Segmentationcited by 796
  7. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  8. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  9. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  10. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  11. 2019Panoptic-DeepLabcited by 362
  12. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  13. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  14. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  15. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  16. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  17. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 222
  18. 2021K-Net: Towards Unified Image Segmentationcited by 211
  19. 2023CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPcited by 178
  20. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  21. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  22. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 165
  23. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  24. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  25. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  26. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  27. 2022Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentationcited by 118
  28. 2020Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Reviewcited by 114
  29. 2019Seamless Scene Segmentationcited by 112
  30. 2021Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentationcited by 107
  31. 2020PointMixup: Augmentation for Point Cloudscited by 104
  32. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 92
  33. 2020AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentationcited by 87
  34. 2020LiDAR-based Panoptic Segmentation via Dynamic Shifting Networkcited by 84
  35. 2021EfficientLPS: Efficient LiDAR Panoptic Segmentationcited by 76
  36. 2023RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Drivingcited by 76
  37. 2022LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perceptioncited by 74
  38. 2022Benchmarking and Analyzing Point Cloud Classification under Corruptionscited by 70

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 19; 2024: 41; 2025: 51; 2026: 15.

126 papers.

Sort:

By area:

  1. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  2. 2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 128
  3. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 123
  4. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 85
  5. 2023UniPAD: A Universal Pre-training Paradigm for Autonomous Drivingcited by 73
  6. 2024SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Groundingcited by 66
  7. 20253D and 4D World Modeling: A Surveycited by 64
  8. 2023UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebasecited by 57
  9. 2023Towards Label-free Scene Understanding by Vision Foundation Modelscited by 54
  10. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 53
  11. 2023FRNet: Frustum-Range Networks for Scalable LiDAR Segmentationcited by 50
  12. 2023RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptionscited by 47
38 more
  1. 2023HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Cloudscited by 45
  2. 2024Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Drivingcited by 39
  3. 2024RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radarcited by 32
  4. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 32
  5. 2025Vision-Language-Action Models for Autonomous Driving: Past, Present, and Futurecited by 32
  6. 2024Is Your HD Map Constructor Reliable under Sensor Corruptions?cited by 28
  7. 2024DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Drivingcited by 27
  8. 2024Is Your LiDAR Placement Optimized for 3D Scene Understanding?cited by 25
  9. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  10. 2024Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunitiescited by 24
  11. 2024Multi-Space Alignments Towards Universal LiDAR Segmentationcited by 24
  12. 2023See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Datacited by 21
  13. 2025LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenescited by 19
  14. 2025Perspective-Invariant 3D Object Detectioncited by 16
  15. 2024RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentationcited by 15
  16. 2024LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splattingcited by 15
  17. 2024Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weathercited by 14
  18. 2025LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequencescited by 14
  19. 2023The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimationcited by 13
  20. 2023TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentationcited by 13
  21. 2024TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentationcited by 13
  22. 2024SFPNet: Sparse Focal Point Network for Semantic Segmentation on General LiDAR Point Cloudscited by 13
  23. 2025PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learningcited by 13
  24. 2024An Empirical Study of Training State-of-the-Art LiDAR Segmentation Modelscited by 12
  25. 2025SafeMap: Robust HD Map Construction from Incomplete Observationscited by 12
  26. 2024Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understandingcited by 11
  27. 2025LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Drivingcited by 11
  28. 2025SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understandingcited by 10
  29. 2024Reflectivity Is All You Need!: Advancing LiDAR Semantic Segmentationcited by 9
  30. 2024A Point-Based Approach to Efficient LiDAR Multi-Task Perceptioncited by 9
  31. 2025LeAP: Consistent multi-domain 3D labeling using Foundation Modelscited by 8
  32. 2025Label-Efficient LiDAR Semantic Segmentation with 2D-3D Vision Transformer Adapterscited by 8
  33. 20254D Driving Scene Generation With Stereo Forcingcited by 8
  34. 20253EED: Ground Everything Everywhere in 3Dcited by 8
  35. 2024Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Cloudscited by 7
  36. 2025How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentationcited by 7
  37. 2025Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representationscited by 7
  38. 2023CurveCloudNet: Processing Point Clouds with 1D Structurecited by 5

50 most cited of 126 All 126 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generation
  2. 2022Generative Range Imaging for Learning Scene Priors of 3D LiDAR Data
  3. 2025Range-Edit: Semantic Mask Guided Outdoor LiDAR Scene Editing
  4. 2026Adversarially Guided Diffusion for LiDAR Range Image Synthesis
  5. 2024DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models
  6. 2026Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point Transformers
  7. 2025LOSC: LiDAR Open-voc Segmentation Consolidator
  8. 2026Geometry Without Coordinates: LiDAR Diffusion as a 3D Feature Bridge