Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers (2401.01552v2)

Published 3 Jan 2024 in cs.CV

Abstract: Point cloud completion is an indispensable task for recovering complete point clouds due to incompleteness caused by occlusion, limited sensor resolution, etc. The family of coarse-to-fine generation architectures has recently exhibited great success in point cloud completion and gradually became mainstream. In this work, we unveil one of the key ingredients behind these methods: meticulously devised feature extraction operations with explicit cross-resolution aggregation. We present Cross-Resolution Transformer that efficiently performs cross-resolution aggregation with local attention mechanisms. With the help of our recursive designs, the proposed operation can capture more scales of features than common aggregation operations, which is beneficial for capturing fine geometric characteristics. While prior methodologies have ventured into various manifestations of inter-level cross-resolution aggregation, the effectiveness of intra-level one and their combination has not been analyzed. With unified designs, Cross-Resolution Transformer can perform intra- or inter-level cross-resolution aggregation by switching inputs. We integrate two forms of Cross-Resolution Transformers into one up-sampling block for point generation, and following the coarse-to-fine manner, we construct CRA-PCN to incrementally predict complete shapes with stacked up-sampling blocks. Extensive experiments demonstrate that our method outperforms state-of-the-art methods by a large margin on several widely used benchmarks. Codes are available at https://github.com/EasyRy/CRA-PCN.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age. IEEE Transactions on robotics, 32(6): 1309–1332.
  2. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012.
  3. Multi-view 3d object detection network for autonomous driving. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 1907–1915.
  4. AnchorFormer: Point Cloud Completion From Discriminative Nodes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 13581–13590.
  5. 4d spatio-temporal convnets: Minkowski convolutional neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 3075–3084.
  6. 3d-r2n2: A unified approach for single and multi-view 3d object reconstruction. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII 14, 628–644. Springer.
  7. A point set generation network for 3d object reconstruction from a single image. In Proceedings of the IEEE conference on computer vision and pattern recognition, 605–613.
  8. Learning a predictable and generative vector representation for objects. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VI 14, 484–499. Springer.
  9. Pct: Point cloud transformer. Computational Visual Media, 7: 187–199.
  10. High-resolution shape completion using deep neural networks for global structure and local geometry inference. In Proceedings of the IEEE international conference on computer vision, 85–93.
  11. Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 5354–5363.
  12. Pf-net: Point fractal network for 3d point cloud completion. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 7662–7670.
  13. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  14. Pointpillars: Fast encoders for object detection from point clouds. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 12697–12705.
  15. Vehicle detection from 3d lidar using fully convolutional network. arXiv preprint arXiv:1608.07916.
  16. ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9466–9475.
  17. Morphing and sampling network for dense point cloud completion. In Proceedings of the AAAI conference on artificial intelligence, volume 34, 11596–11603.
  18. Voxnet: A 3d convolutional neural network for real-time object recognition. In 2015 IEEE/RSJ international conference on intelligent robots and systems (IROS), 922–928. IEEE.
  19. Pan, L. 2020. ECG: Edge-aware point cloud completion with graph convolution. IEEE Robotics and Automation Letters, 5(3): 4392–4398.
  20. Variational relational point completion network. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 8524–8533.
  21. Multi-view partial (mvp) point cloud challenge 2021 on completion and registration: Methods and results. arXiv preprint arXiv:2112.12053.
  22. Fast point transformer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16949–16958.
  23. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32.
  24. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 652–660.
  25. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 30.
  26. Pu-gcn: Point cloud upsampling using graph convolutional networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 11683–11692.
  27. Carfusion: Combining point tracking and part detection for dynamic 3d reconstruction of vehicles. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1906–1915.
  28. Octnet: Learning deep 3d representations at high resolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, 3577–3586.
  29. Towards 3D point cloud based object maps for household environments. Robotics and Autonomous Systems, 56(11): 927–941.
  30. Dynamic edge-conditioned filters in convolutional neural networks on graphs. In Proceedings of the IEEE conference on computer vision and pattern recognition, 3693–3702.
  31. Semantic scene completion from a single depth image. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1746–1754.
  32. LAKe-Net: topology-aware point cloud completion by localizing aligned keypoints. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 1726–1735.
  33. What do single-view 3d reconstruction networks learn? In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 3405–3414.
  34. Topnet: Structural point cloud decoder. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 383–392.
  35. Kpconv: Flexible and deformable convolution for point clouds. In Proceedings of the IEEE/CVF international conference on computer vision, 6411–6420.
  36. Attention is all you need. Advances in neural information processing systems, 30.
  37. Cascaded refinement network for point cloud completion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 790–799.
  38. Dynamic graph cnn for learning on point clouds. Acm Transactions On Graphics (tog), 38(5): 1–12.
  39. Learning local displacements for point cloud completion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1568–1577.
  40. Point cloud completion by skip-attention network with hierarchical folding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1939–1948.
  41. Pmp-net: Point cloud completion by learning multi-step point moving paths. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 7443–7452.
  42. Pointconv: Deep convolutional networks on 3d point clouds. In Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition, 9621–9630.
  43. Snowflakenet: Point cloud completion by snowflake point deconvolution with skip-transformer. In Proceedings of the IEEE/CVF international conference on computer vision, 5499–5509.
  44. Grnet: Gridding residual network for dense point cloud completion. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part IX, 365–381. Springer.
  45. Spidercnn: Deep learning on point sets with parameterized convolutional filters. In Proceedings of the European conference on computer vision (ECCV), 87–102.
  46. Fbnet: Feedback network for point cloud completion. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part II, 676–693. Springer.
  47. Foldingnet: Point cloud auto-encoder via deep grid deformation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 206–215.
  48. Patch-based progressive 3d point set upsampling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 5958–5967.
  49. Pointr: Diverse point cloud completion with geometry-aware transformers. In Proceedings of the IEEE/CVF international conference on computer vision, 12498–12507.
  50. Pcn: Point completion network. In 2018 international conference on 3D vision (3DV), 728–737. IEEE.
  51. Pointweb: Enhancing local neighborhood features for point cloud processing. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 5565–5573.
  52. Point transformer. In Proceedings of the IEEE/CVF international conference on computer vision, 16259–16268.
  53. Seedformer: Patch seeds based point cloud completion with upsample transformer. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part III, 416–432. Springer.
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now