mlsanityData to 7 Oct 2026

(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network

arXiv 2102.04530 ↗First posted 8 Feb 2021cs.CV cs.AI cs.ROcited by 164

Not on the map. Why?

Abstract (arXiv)

Autonomous robotic systems and self driving cars rely on accurate perception of their surroundings as the safety of the passengers and pedestrians is the top priority. Semantic segmentation is one the essential components of environmental perception that provides semantic information of the scene. Recently, several methods have been introduced for 3D LiDAR semantic segmentation. While, they can lead to improved performance, they are either afflicted by high computational complexity, therefore are inefficient, or lack fine details of smaller instances. To alleviate this problem, we propose AF2-S3Net, an end-to-end encoder-decoder CNN network for 3D LiDAR semantic segmentation. We present a novel multi-branch attentive feature fusion module in the encoder and a unique adaptive feature selection module with feature map re-weighting in the decoder. Our AF2-S3Net fuses the voxel based learning and point-based learning into a single framework to effectively process the large 3D scene. Our experimental results show that the proposed method outperforms the state-of-the-art approaches on the large-scale SemanticKITTI benchmark, ranking 1st on the competitive public leaderboard competition upon publication.

Key facts. Cited by 164 papers in the map (data through 7 Oct 2026). Builds on 32 of its 47 references that are in the map. First posted on arXiv 8 Feb 2021.

Builds on

32 of 47 references.

References · 32

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017Squeeze-and-Excitation Networkscited by 4,763
  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. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  6. 2018YOLOv3: An Incremental Improvementcited by 2,652
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  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. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  11. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  12. 2017Progressive Neural Architecture Searchcited by 483
20 more
  1. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  2. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  3. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  4. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  5. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  6. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  7. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  8. 2020Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentationcited by 112
  9. 2020S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Cloudscited by 102
  10. 2020AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentationcited by 87
  11. 20203D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentationcited by 58
  12. 2019SalsaNet: Fast Road and Vehicle Segmentation in LiDAR Point Clouds for Autonomous Drivingcited by 57
  13. 2020KPRNet: Improving projection-based LiDAR semantic segmentationcited by 47
  14. 20183D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizescited by 42
  15. 2019LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Latticescited by 38
  16. 2018VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D Shapescited by 37
  17. 2020Depth Based Semantic Scene Completion with Position Importance Aware Losscited by 36
  18. 2020TORNADO-Net: mulTiview tOtal vaRiatioN semAntic segmentation with Diamond inceptiOn modulecited by 36
  19. 2019Bayesian Spatial Kernel Smoothing for Scalable Dense Semantic Mappingcited by 34
  20. 2020MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Viewscited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 35; 2023: 60; 2024: 30; 2025: 20; 2026: 2.

164 papers.

Sort:

By area:

  1. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  2. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  3. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  4. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 287
  5. 2023OccWorld: Learning a 3D Occupancy World Model for Autonomous Drivingcited by 230
  6. 2023CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPcited by 178
  7. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  8. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 165
  9. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  10. 2023Rethinking Range View Representation for LiDAR Segmentationcited by 126
  11. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 124
  12. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
38 more
  1. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 123
  2. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  3. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  4. 2022Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentationcited by 118
  5. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 114
  6. 2021FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detectioncited by 92
  7. 2024GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Predictioncited by 83
  8. 2023SCPNet: Semantic Scene Completion on Point Cloudcited by 80
  9. 2022LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perceptioncited by 74
  10. 2023SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Drivingcited by 72
  11. 2023MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Drivingcited by 68
  12. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  13. 2021Learning 3D Semantic Segmentation with only 2D Image Supervisioncited by 60
  14. 2021EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentationcited by 59
  15. 2022Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmapcited by 59
  16. 2023UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebasecited by 57
  17. 2023Towards Label-free Scene Understanding by Vision Foundation Modelscited by 54
  18. 2023Using a Waffle Iron for Automotive Point Cloud Semantic Segmentationcited by 53
  19. 2023PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Predictioncited by 51
  20. 2023FRNet: Frustum-Range Networks for Scalable LiDAR Segmentationcited by 50
  21. 2022SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Cloudscited by 49
  22. 2021FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decodingcited by 46
  23. 20233D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Cloudscited by 46
  24. 2022LESS: Label-Efficient Semantic Segmentation for LiDAR Point Cloudscited by 41
  25. 2021GP-S3Net: Graph-based Panoptic Sparse Semantic Segmentation Networkcited by 37
  26. 2022GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentationcited by 36
  27. 2023TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUscited by 36
  28. 2021LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentationcited by 34
  29. 2024OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Predictioncited by 32
  30. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 32
  31. 2022Open-world Semantic Segmentation for LIDAR Point Cloudscited by 29
  32. 2022PointConvFormer: Revenge of the Point-based Convolutioncited by 29
  33. 2023LinK: Linear Kernel for LiDAR-based 3D Perceptioncited by 26
  34. 2024Multi-Space Alignments Towards Universal LiDAR Segmentationcited by 24
  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. 2023Spatiotemporal Self-supervised Learning for Point Clouds in the Wildcited by 23
  38. 2023Clustering based Point Cloud Representation Learning for 3D Analysiscited by 23

50 most cited of 164 All 164 (JSON)