mlsanityData to 14 Oct 2026

Long Range Pooling for 3D Large-Scale Scene Understanding

arXiv 2301.06962 ↗First posted 17 Jan 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Inspired by the success of recent vision transformers and large kernel design in convolutional neural networks (CNNs), in this paper, we analyze and explore essential reasons for their success. We claim two factors that are critical for 3D large-scale scene understanding: a larger receptive field and operations with greater non-linearity. The former is responsible for providing long range contexts and the latter can enhance the capacity of the network. To achieve the above properties, we propose a simple yet effective long range pooling (LRP) module using dilation max pooling, which provides a network with a large adaptive receptive field. LRP has few parameters, and can be readily added to current CNNs. Also, based on LRP, we present an entire network architecture, LRPNet, for 3D understanding. Ablation studies are presented to support our claims, and show that the LRP module achieves better results than large kernel convolution yet with reduced computation, due to its nonlinearity. We also demonstrate the superiority of LRPNet on various benchmarks: LRPNet performs the best on ScanNet and surpasses other CNN-based methods on S3DIS and Matterport3D. Code will be made publicly available.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 66 of its 83 references that are in the map. First posted on arXiv 17 Jan 2023.

Builds on

66 of 83 references.

References · 66

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  8. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  9. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  10. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  11. 2022A ConvNet for the 2020scited by 3,579
  12. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
38 more
  1. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  2. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  4. 2020Point Transformercited by 1,470
  5. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  6. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  7. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  9. 2021Transformers in Vision: A Surveycited by 1,013
  10. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  11. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  12. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  13. 2020PCT: Point cloud transformercited by 732
  14. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  15. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  16. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  17. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  18. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 553
  19. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
  20. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
  21. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  22. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  23. 2021Voxel Transformer for 3D Object Detectioncited by 247
  24. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 239
  25. 2021Attention Mechanisms in Computer Vision: A Surveycited by 232
  26. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  27. 2022Visual Attention Networkcited by 210
  28. 2022Focal Modulation Networkscited by 186
  29. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 179
  30. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  31. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 167
  32. 2020DiffusionNet: Discretization Agnostic Learning on Surfacescited by 164
  33. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  34. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  35. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  36. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  37. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  38. 2022More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsitycited by 142

50 most cited of 66 All 66 (JSON)

Built on by

Not cited yet.