mlsanityData to 7 Oct 2026

SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation

arXiv 2205.13490 ↗First posted 26 May 2022cs.CV cs.AI cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Conventional point cloud semantic segmentation methods usually employ an encoder-decoder architecture, where mid-level features are locally aggregated to extract geometric information. However, the over-reliance on these class-agnostic local geometric representations may raise confusion between local parts from different categories that are similar in appearance or spatially adjacent. To address this issue, we argue that mid-level features can be further enhanced with semantic information, and propose semantic-affine transformation that transforms features of mid-level points belonging to different categories with class-specific affine parameters. Based on this technique, we propose SemAffiNet for point cloud semantic segmentation, which utilizes the attention mechanism in the Transformer module to implicitly and explicitly capture global structural knowledge within local parts for overall comprehension of each category. We conduct extensive experiments on the ScanNetV2 and NYUv2 datasets, and evaluate semantic-affine transformation on various 3D point cloud and 2D image segmentation baselines, where both qualitative and quantitative results demonstrate the superiority and generalization ability of our proposed approach. Code is available at https://github.com/wangzy22/SemAffiNet.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 66 of its 74 references that are in the map. First posted on arXiv 26 May 2022.

Builds on

66 of 74 references.

References · 66

  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. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  9. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  10. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  11. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  12. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
38 more
  1. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  2. 2016Pyramid Scene Parsing Networkcited by 2,472
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  4. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  5. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  6. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  7. 2020Point Transformercited by 1,462
  8. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  10. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  11. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  12. 2016An overview of gradient descent optimization algorithmscited by 1,021
  13. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  14. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  15. 2020PCT: Point cloud transformercited by 730
  16. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  17. 2019Panoptic Feature Pyramid Networkscited by 644
  18. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  19. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  20. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  21. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  22. 2016Convolutional Pose Machinescited by 325
  23. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
  24. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  25. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  26. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  27. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  28. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  29. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  30. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  31. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  32. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  33. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  34. 2016SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networkscited by 134
  35. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  36. 20183DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentationcited by 118
  37. 2020Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentationcited by 112
  38. 2020PointMixup: Augmentation for Point Cloudscited by 104

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 5; 2025: 3.

11 papers.

  1. 20232D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervisioncited by 16
  2. 2023Generalized Few-Shot Point Cloud Segmentation Via Geometric Wordscited by 12
  3. 20243D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidancecited by 12
  4. 2023MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memorycited by 9
  5. 2024Unsupervised Template-assisted Point Cloud Shape Correspondence Networkcited by 7
  6. 2024Localization and Expansion: A Decoupled Framework for Point Cloud Few-shot Semantic Segmentationcited by 6
  7. 2024Deep Learning on 3D Semantic Segmentation: A Detailed Reviewcited by 6
  8. 2025BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysiscited by 5
  9. 20253D Weakly Supervised Semantic Segmentation via Class-Aware and Geometry-Guided Pseudo-Label Refinementcited by 1
  10. 2024Towards Semi-supervised Dual-modal Semantic Segmentationcited by 0
  11. 2025PointVDP: Learning View-Dependent Projection by Fireworks Rays for 3D Point Cloud Segmentationcited by 0