mlsanityData to 7 Oct 2026

Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation

arXiv 2301.10100 ↗First posted 24 Jan 2023cs.CVcited by 53

Not on the map. Why?

Abstract (arXiv)

Semantic segmentation of point clouds in autonomous driving datasets requires techniques that can process large numbers of points efficiently. Sparse 3D convolutions have become the de-facto tools to construct deep neural networks for this task: they exploit point cloud sparsity to reduce the memory and computational loads and are at the core of today's best methods. In this paper, we propose an alternative method that reaches the level of state-of-the-art methods without requiring sparse convolutions. We actually show that such level of performance is achievable by relying on tools a priori unfit for large scale and high-performing 3D perception. In particular, we propose a novel 3D backbone, WaffleIron, made almost exclusively of MLPs and dense 2D convolutions and present how to train it to reach high performance on SemanticKITTI and nuScenes. We believe that WaffleIron is a compelling alternative to backbones using sparse 3D convolutions, especially in frameworks and on hardware where those convolutions are not readily available.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Builds on 39 of its 63 references that are in the map. First posted on arXiv 24 Jan 2023.

Builds on

39 of 63 references.

References · 39

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2020Point Transformercited by 1,462
  7. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  9. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  10. 2016Deep Networks with Stochastic Depthcited by 973
  11. 2021Going deeper with Image Transformerscited by 759
  12. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
27 more
  1. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  2. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  3. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  4. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  5. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  6. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  7. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  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. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 187
  11. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  12. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  13. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  14. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  15. 2022Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentationcited by 118
  16. 2021Fast Point Transformercited by 103
  17. 2020AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentationcited by 87
  18. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  19. 2022TorchSparse: Efficient Point Cloud Inference Enginecited by 72
  20. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
  21. 2020KPRNet: Improving projection-based LiDAR semantic segmentationcited by 47
  22. 2019LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Latticescited by 38
  23. 2021Lite-HDSeg: LiDAR Semantic Segmentation Using Lite Harmonic Dense Convolutionscited by 37
  24. 2020TORNADO-Net: mulTiview tOtal vaRiatioN semAntic segmentation with Diamond inceptiOn modulecited by 36
  25. 2022GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentationcited by 36
  26. 2022PCSCNet: Fast 3D Semantic Segmentation of LiDAR Point Cloud for Autonomous Car using Point Convolution and Sparse Convolution Networkcited by 14
  27. 2020Cascaded Non-local Neural Network for Point Cloud Semantic Segmentationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 9; 2024: 14; 2025: 18; 2026: 12.

53 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. 2023UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebasecited by 57
  7. 2023FRNet: Frustum-Range Networks for Scalable LiDAR Segmentationcited by 50
  8. 2023Three Pillars improving Vision Foundation Model Distillation for Lidarcited by 43
  9. 2023PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awarenesscited by 42
  10. 2024Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Drivingcited by 39
  11. 2024Is Your LiDAR Placement Optimized for 3D Scene Understanding?cited by 25
  12. 2024Multi-Space Alignments Towards Universal LiDAR Segmentationcited by 24
38 more
  1. 2025LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenescited by 19
  2. 2025Perspective-Invariant 3D Object Detectioncited by 16
  3. 2024MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perceptioncited by 15
  4. 2024Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weathercited by 14
  5. 2024SFPNet: Sparse Focal Point Network for Semantic Segmentation on General LiDAR Point Cloudscited by 13
  6. 2024An Empirical Study of Training State-of-the-Art LiDAR Segmentation Modelscited by 12
  7. 2024Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understandingcited by 11
  8. 2025LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Drivingcited by 11
  9. 2025HiMo: High-Speed Objects Motion Compensation in Point Cloudscited by 11
  10. 2025SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understandingcited by 10
  11. 2025LeAP: Consistent multi-domain 3D labeling using Foundation Modelscited by 8
  12. 20253EED: Ground Everything Everywhere in 3Dcited by 8
  13. 2024Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Modelscited by 5
  14. 2025NUC-Net: Non-uniform Cylindrical Partition Network for Efficient LiDAR Semantic Segmentationcited by 5
  15. 2025LOSC: LiDAR Open-voc Segmentation Consolidatorcited by 5
  16. 2024Exploiting Local Features and Range Images for Small Data Real-Time Point Cloud Semantic Segmentationcited by 4
  17. 2025SALT: A Flexible Semi-Automatic Labeling Tool for General LiDAR Point Clouds with Cross-Scene Adaptability and 4D Consistencycited by 4
  18. 2025FLARES: Fast and Accurate LiDAR Multi-Range Semantic Segmentationcited by 3
  19. 2025Real Time Semantic Segmentation of High Resolution Automotive LiDAR Scanscited by 2
  20. 2025Improving Multimodal Distillation for 3D Semantic Segmentation under Domain Shiftcited by 2
  21. 2026Exploring Easy Boosts for Lidar Semantic Scene Completioncited by 2
  22. 2024Are We Ready for Real-Time LiDAR Semantic Segmentation in Autonomous Driving?cited by 1
  23. 2024Calibrated and Efficient Sampling-Free Confidence Estimation for LiDAR Scene Semantic Segmentationcited by 1
  24. 2025Is clustering enough for LiDAR instance segmentation? A state-of-the-art training-free baselinecited by 1
  25. 2025HARP-NeXt: High-Speed and Accurate Range-Point Fusion Network for 3D LiDAR Semantic Segmentationcited by 1
  26. 2026Collaborative Learning for Semi-Supervised LiDAR Semantic Segmentationcited by 1
  27. 2026TOLiD: Bridging the Architecture Gap in Vision Foundation Model to LiDAR Pretraining via Token Lifting for Distillationcited by 1
  28. 2024A Preprocessing and Postprocessing Voxel-based Method for LiDAR Semantic Segmentation Improvement in Long Distancecited by 0
  29. 2024MILAN: Milli-Annotations for Lidar Semantic Segmentationcited by 0
  30. 2025An Experimental Study of SOTA LiDAR Segmentation Modelscited by 0
  31. 2025Depth-Aware Range Image-Based Model for Point Cloud Segmentationcited by 0
  32. 2025DAGLFNet: Deep Feature Attention Guided Global and Local Feature Fusion for Pseudo-Image Point Cloud Segmentationcited by 0
  33. 2026LiDAR-Anchored Collaborative Distillation for Robust 2D Representationscited by 0
  34. 2026Adaptive Augmentation-Aware Latent Learning for Robust LiDAR Semantic Segmentationcited by 0
  35. 2026Efficient Point Cloud Processing with High-Dimensional Positional Encoding and Non-Local MLPscited by 0
  36. 2026IGLOSS: Image Generation for Lidar Open-vocabulary Semantic Segmentationcited by 0
  37. 2026Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Taskscited by 0
  38. 2026Learning to Identify Out-of-Distribution Objects for 3D LiDAR Anomaly Segmentationcited by 0

50 most cited of 53 All 53 (JSON)