mlsanityData to 7 Oct 2026

SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

arXiv 2004.01803 ↗First posted 3 Apr 2020cs.CVcited by 170

Not on the map. Why?

Abstract (arXiv)

LiDAR point-cloud segmentation is an important problem for many applications. For large-scale point cloud segmentation, the textitde facto method is to project a 3D point cloud to get a 2D LiDAR image and use convolutions to process it. Despite the similarity between regular RGB and LiDAR images, we discover that the feature distribution of LiDAR images changes drastically at different image locations. Using standard convolutions to process such LiDAR images is problematic, as convolution filters pick up local features that are only active in specific regions in the image. As a result, the capacity of the network is under-utilized and the segmentation performance decreases. To fix this, we propose Spatially-Adaptive Convolution (SAC) to adopt different filters for different locations according to the input image. SAC can be computed efficiently since it can be implemented as a series of element-wise multiplications, im2col, and standard convolution. It is a general framework such that several previous methods can be seen as special cases of SAC. Using SAC, we build SqueezeSegV3 for LiDAR point-cloud segmentation and outperform all previous published methods by at least 3.7% mIoU on the SemanticKITTI benchmark with comparable inference speed.

Key facts. Cited by 170 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 31; 2022: 48; 2023: 41; 2024: 30; 2025: 13; 2026: 7.

170 papers.

Sort:

By area:

  1. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  2. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  3. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  4. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  5. 2023Rethinking Range View Representation for LiDAR Segmentationcited by 126
  6. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 124
  7. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 123
  8. 2022Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentationcited by 118
  9. 2024FeatUp: A Model-Agnostic Framework for Features at Any Resolutioncited by 114
  10. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 92
  11. 2021Iterative Filter Adaptive Network for Single Image Defocus Deblurringcited by 85
  12. 2023SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Drivingcited by 72
38 more
  1. 2022Scribble-Supervised LiDAR Semantic Segmentationcited by 69
  2. 2023MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Drivingcited by 68
  3. 2022SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehiclescited by 65
  4. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  5. 2021Learning 3D Semantic Segmentation with only 2D Image Supervisioncited by 60
  6. 2021EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentationcited by 59
  7. 2021Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perceptioncited by 57
  8. 2022Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoderscited by 57
  9. 2023UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebasecited by 57
  10. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  11. 2022CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Drivingcited by 56
  12. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 53
  13. 2022STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Datasetcited by 52
  14. 2021Learning Semantic Segmentation of Large-Scale Point Clouds with Random Samplingcited by 51
  15. 2023FRNet: Frustum-Range Networks for Scalable LiDAR Segmentationcited by 50
  16. 2022SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Cloudscited by 49
  17. 2021A Survey on Deep Domain Adaptation for LiDAR Perceptioncited by 46
  18. 2021FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decodingcited by 46
  19. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generationcited by 45
  20. 2021Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Modelscited by 41
  21. 2021ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenationcited by 41
  22. 2022LESS: Label-Efficient Semantic Segmentation for LiDAR Point Cloudscited by 41
  23. 2021Lite-HDSeg: LiDAR Semantic Segmentation Using Lite Harmonic Dense Convolutionscited by 37
  24. 2021Semantic Segmentation-assisted Scene Completion for LiDAR Point Cloudscited by 37
  25. 2022GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentationcited by 36
  26. 2023Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentationcited by 33
  27. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 32
  28. 2021Deep Learning Based 3D Segmentation: A Surveycited by 30
  29. 2022PointConvFormer: Revenge of the Point-based Convolutioncited by 29
  30. 2021LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignmentcited by 26
  31. 2023LinK: Linear Kernel for LiDAR-based 3D Perceptioncited by 26
  32. 2021Efficient 3D Deep LiDAR Odometrycited by 25
  33. 2022Domain generalization of 3D semantic segmentation in autonomous drivingcited by 25
  34. 2024Is Your LiDAR Placement Optimized for 3D Scene Understanding?cited by 25
  35. 2021DRINet++: Efficient Voxel-as-point Point Cloud Segmentationcited by 23
  36. 2022Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregationcited by 23
  37. 2022Open-Vocabulary 3D Detection via Image-level Class and Debiased Cross-modal Contrastive Learningcited by 23
  38. 2023Clustering based Point Cloud Representation Learning for 3D Analysiscited by 23

50 most cited of 170 All 170 (JSON)