CoChat
Sign Up
Cited by 2,1003D Shape Modeling and AnalysisAdvanced Neural Network ApplicationsDomain Adaptation and Few-Shot Learning

The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.

PCT: Point cloud transformer

Open access
Guo, Meng-Hao, Cai, Jun-Xiong, Liu, Zheng-Ning, Mu, Tai-Jiang, Martin, Ralph R., Hu, Shi-Min·2021·Computational Visual Media
DOI 10.1007/s41095-021-0229-5
Open this paper in CoChat — free accountOpen PDF

Abstract

The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Transformer (PCT) for point cloud learning. PCT is based on Transformer, which achieves huge success in natural language processing and displays great potential in image processing. It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning. To better capture local context within the point cloud, we enhance input embedding with the support of farthest point sampling and nearest neighbor search. Extensive experiments demonstrate that the PCT achieves the state-of-the-art performance on shape classification, part segmentation, semantic segmentation, and normal estimation tasks.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s41095-021-0229-5

Cites

22 of 22 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 2 PCT architecture. The encoder mainly comprises an Input Embedding module and four stacked Attention module. The decoder mainly comprises multiple Linear layers. Numbers above each module indicate its output channels. MA-Pool concatenates Max-Pool and Average-Pool . LBR combines Linear , BatchNorm , and ReLU layers. LBRD means LBR followed by a Dropout layer.
Fig. 2 PCT architecture. The encoder mainly comprises an Input Embedding module and four stacked Attention module. The decoder mainly comprises multiple Linear layers. Numbers above each module indicate its output channels. MA-Pool concatenates Max-Pool and Average-Pool . LBR combines Linear , BatchNorm , and ReLU layers. LBRD means LBR followed by a Dropout layer.CC-BY · From the PDF
Image 2
CC-BY · From the PDF
Fig. 4 Left: Neighbor Embedding architecture. Middle: SG module with N in input points, d in input channels, k neighbors, N out output sampled points, and d out output channels. Top-right: example of sampling (colored balls represent sampled points). Bottom-right: example of grouping with k -NN neighbors. Number above LBR: number of output channels. Number above SG: number of sampled points and its output channels.
Fig. 4 Left: Neighbor Embedding architecture. Middle: SG module with N in input points, d in input channels, k neighbors, N out output sampled points, and d out output channels. Top-right: example of sampling (colored balls represent sampled points). Bottom-right: example of grouping with k -NN neighbors. Number above LBR: number of output channels. Number above SG: number of sampled points and its output channels.CC-BY · From the PDF
Fig. 5 Segmentations from PointNet, NPCT, SPCT, PCT, and ground truth (GT).
Fig. 5 Segmentations from PointNet, NPCT, SPCT, PCT, and ground truth (GT).CC-BY · From the PDF
Image 5
CC-BY · From the PDF
Image 6
CC-BY · From the PDF
Image 7
CC-BY · From the PDF
Image 8
CC-BY · From the PDF
Image 9
CC-BY · From the PDF
Image 10
CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 20

  1. Charles, R. Q.; Hao, S.; Mo, K. C.; Guibas, L. J. PointNet: Deep learning on point sets for 3D classification and segmentation. IN: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 77–85, 2017.
  2. Tchapmi, L. P.; Choy, C. B.; Armeni, I.; Gwak, J.; Savarese, S. SEGCloud: Semantic segmentation of 3D point clouds. In: Proceedings of the International Conference on 3D Vision, 537–547, 2017.
  3. Wu, W. X.; Qi, Z.; Fuxin, L. PointConv: Deep convolutional networks on 3D point clouds. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9613–9622, 2019.
  4. Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A. N.; Kaiser, L.; Polosukhin, I. Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing, 6000–6010, 2017.
  5. Bruna, J.; Zaremba, W.; Szlam, A.; LeCun, Y. Spectral networks and locally connected networks on graphs. In: Proceedings of the International Conference on Learning Representations, 2014.
  6. Hu, S.-M.; Liang, D.; Yang, G.-Y.; Yang, G.-W.; Zhou, W.-Y. Jittor: A novel deep learning framework with meta-operators and unified graph execution. Science China Information Sciences Vol. 63, No. 12, Article No. 222103, 2020.
  7. Bahdanau, D.; Cho, K. H.; Bengio, Y. Neural machine translation by jointly learning to align and translate. In: Proceedings of the 3rd International Conference on Learning Representations, 2015.
  8. Lin, Z.; Feng, M.; dos Santos, C. N.; Yu, M.; Xiang, B.; Zhou, B.; Bengio, Y. A structured self-attentive sentence embedding. In: Proceedings of the International Conference on Learning Representations, 2017.
  9. Yang, Z.; Dai, Z.; Yang, Y.; Carbonell, J. G.; Salakhutdinov, R.; Le, Q. V. XLNet: Generalized autoregressive pretraining for language understanding. In: Proceedings of the 33rd Conference on Neural Information Processing Systems, 5754–5764, 2019.
  10. Qi, C. R.; Yi, L.; Su, H.; Guibas, L. J. PointNet++: Deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the 31st Conference on Neural Information Processing Systems, 5099–5108, 2017.
  11. Yang, Y. Q.; Liu, S. L.; Pan, H.; Liu, Y.; Tong, X. PFCNN: Convolutional neural networks on 3D surfaces using parallel frames. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 13575–13584, 2020.
  12. Yan, X.; Zheng, C. D.; Li, Z.; Wang, S.; Cui, S. G. PointASNL: Robust point clouds processing using nonlocal neural networks with adaptive sampling. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 5588–5597, 2020.
  13. Hertz, A.; Hanocka, R.; Giryes, R.; Cohen-Or, D. PointGMM: A neural GMM network for point clouds. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 12051–12060, 2020.
  14. Wang, Y.; Solomon, J. Deep closest point: Learning representations for point cloud registration. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, 3522–3531, 2019.
  15. Li, J. X.; Chen, B. M.; Lee, G. H. SO-net: Self-organizing network for point cloud analysis. In: Proceeding of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9397–9406, 2018.
  16. Klokov, R.; Lempitsky, V. Escape from cells: Deep kdnetworks for the recognition of 3D point cloud models. In: Proceeding of the IEEE International Conference on Computer Vision, 863–872, 2017.
  17. Le, T.; Duan, Y. PointGrid: A deep network for 3D shape understanding. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9204–9214, 2018.
  18. Zhao, H.; Jiang, L.; Fu, C.; Jia, J. PointWeb: Enhancing local neighborhood features for point cloud processing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5560–5568, 2019.
  19. Komarichev, A.; Zhong, Z. C.; Hua, J. A-CNN: Annularly convolutional neural networks on point clouds. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 7413–7422, 2019.
  20. Thomas, H.; Qi, C. R.; Deschaud, J. E.; Marcotegui, B.; Goulette, F.; Guibas, L. KPConv: Flexible and deformable convolution for point clouds. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, 6410–6419, 2019.

Cited by

Sorted by citations

  • Untitled work

    Han (2023) · doi:10.1109/tpami.2022.3152247 · Cited by 4,682

    Self-citation

  • Transformers in Vision: A Survey

    Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022) · ACM Computing Surveys · doi:10.1145/3505244 · Cited by 3,595

  • Attention mechanisms in computer vision: A survey

    Guo, M.-H., Xu, T.-X., Liu, J.-J., Liu, Z.-N., Jiang, P.-T., Mu, T.-J., Zhang, S.-H., Martin, R. R., Cheng, M.-M., & Hu, S.-M. (2022) · Computational Visual Media · doi:10.1007/s41095-022-0271-y · Cited by 2,566

    “Recently, various pure deep self-attention networks (visual transformers) [27], [34], [44], [45], [46], [47], [48], [49] have appeared, showing the huge potential of attention-based models.”
    BackgroundInfluentialSelf-citation

  • Multiscale vision transformers

    Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., & Feichtenhofer, C. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00675 · Cited by 1,407

    “An emerging thread of work aims at applying transformers to vision tasks such as object detection [5], semantic segmentation [121, 105], 3D reconstruction [77], pose estimation [113], generative modeling [17], image retrieval [30], medical image segmentation [16,103,117], point clouds [45], video instance segmentation…”
    Background

  • Visual attention network

    Guo, M.-H., Lu, C.-Z., Liu, Z.-N., Cheng, M., & Hu, S. (2023) · Computational Visual Media · doi:10.1007/s41095-023-0364-2 · Cited by 1,235

    Self-citation

See all 2,100

Related

See all

Metadata

Authors
Guo, M.-H., Cai, J.-X., Liu, Z.-N., Mu, T.-J., Martin, R. R., & Hu, S.-M.
Affiliations
  • Tsinghua University (CN)
  • Cardiff University (GB)
Venue
Computational Visual Media
Publisher
Tsinghua University Press
Published
2021-06
Volume
7
Issue
2
Pages
187-199
ISSN
  • 2096-0433 (ISSN-L)
  • 2096-0662
DOI
10.1007/s41095-021-0229-5
OpenAlex
W3111535274
Cited by
2,100
References
17
Citations by year
2026: 309 · 2025: 505 · 2024: 515 · 2023: 428 · 2022: 266 · 2021: 76
FWCI
182.77
Type
journal article
Language
en
Open access
Licence
Locations
  • Computational Visual Media (publishedVersion, cc-by)
  • ORCA Online Research @Cardiff (Cardiff University) (acceptedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • Deutsche Forschungsgemeinschaft
  • National Natural Science Foundation of China (61761136018, 61521002)
Topics
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › 3D Shape Modeling and Analysis
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
point cloud processing, point cloud transformer, transformer models, permutation invariance, farthest point sampling, nearest neighbor search, shape classification, part segmentation, semantic segmentation, surface normal estimation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review