Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling (2312.15133v1)

Published 23 Dec 2023 in cs.CV

Abstract: Point cloud upsampling aims to generate dense and uniformly distributed point sets from a sparse point cloud, which plays a critical role in 3D computer vision. Previous methods typically split a sparse point cloud into several local patches, upsample patch points, and merge all upsampled patches. However, these methods often produce holes, outliers or nonuniformity due to the splitting and merging process which does not maintain consistency among local patches. To address these issues, we propose a novel approach that learns an unsigned distance field guided by local priors for point cloud upsampling. Specifically, we train a local distance indicator (LDI) that predicts the unsigned distance from a query point to a local implicit surface. Utilizing the learned LDI, we learn an unsigned distance field to represent the sparse point cloud with patch consistency. At inference time, we randomly sample queries around the sparse point cloud, and project these query points onto the zero-level set of the learned implicit field to generate a dense point cloud. We justify that the implicit field is naturally continuous, which inherently enables the application of arbitrary-scale upsampling without necessarily retraining for various scales. We conduct comprehensive experiments on both synthetic data and real scans, and report state-of-the-art results under widely used benchmarks.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Computing and rendering point set surfaces. IEEE Transactions on visualization and computer graphics, 9(1): 3–15.
  2. The ball-pivoting algorithm for surface reconstruction. IEEE transactions on visualization and computer graphics, 5(4): 349–359.
  3. Gridpull: Towards scalability in learning implicit representations from 3d point clouds. In Proceedings of the ieee/cvf international conference on computer vision, 18322–18334.
  4. Unsupervised inference of signed distance functions from single sparse point clouds without learning priors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 17712–17723.
  5. Learning implicit fields for generative shape modeling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 5939–5948.
  6. Neural point cloud rendering via multi-plane projection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 7830–7839.
  7. Dell’Eva, A.; et al. 2022. Arbitrary point cloud upsampling with spherical mixture of gaussians. In 2022 International Conference on 3D Vision (3DV), 465–474. IEEE.
  8. The farthest point strategy for progressive image sampling. IEEE Transactions on Image Processing, 6(9): 1305–1315.
  9. Neural points: Point cloud representation with neural fields for arbitrary upsampling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 18633–18642.
  10. Vision meets robotics: The kitti dataset. The International Journal of Robotics Research, 32(11): 1231–1237.
  11. Generative adversarial nets. Advances in neural information processing systems, 27.
  12. 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.
  13. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, 4700–4708.
  14. Consolidation of unorganized point clouds for surface reconstruction. ACM transactions on graphics (TOG), 28(5): 1–7.
  15. Edge-aware point set resampling. ACM transactions on graphics (TOG), 32(1): 1–12.
  16. Multi-grid representation with field regularization for self-supervised surface reconstruction from point clouds. Computers & Graphics.
  17. Pu-gan: a point cloud upsampling adversarial network. In Proceedings of the IEEE/CVF international conference on computer vision, 7203–7212.
  18. Point cloud upsampling via disentangled refinement. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 344–353.
  19. Parameterization-free projection for geometry reconstruction. ACM Transactions on Graphics (TOG), 26(3): 22–es.
  20. Spu-net: Self-supervised point cloud upsampling by coarse-to-fine reconstruction with self-projection optimization. IEEE Transactions on Image Processing, 31: 4213–4226.
  21. Pc2-pu: Patch correlation and point correlation for effective point cloud upsampling. In Proceedings of the 30th ACM International Conference on Multimedia, 2191–2201.
  22. Pu-eva: An edge-vector based approximation solution for flexible-scale point cloud upsampling. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 16208–16217.
  23. Neural-Pull: Learning Signed Distance Function from Point clouds by Learning to Pull Space onto Surface. In International Conference on Machine Learning, 7246–7257. PMLR.
  24. Towards better gradient consistency for neural signed distance functions via level set alignment. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 17724–17734.
  25. Ma, B.; et al. 2022. Reconstructing surfaces for sparse point clouds with on-surface priors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 6315–6325.
  26. Occupancy networks: Learning 3d reconstruction in function space. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 4460–4470.
  27. Implicit surface representations as layers in neural networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 4743–4752.
  28. Nerf: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM, 65(1): 99–106.
  29. Deepsdf: Learning continuous signed distance functions for shape representation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 165–174.
  30. Pu-gcn: Point cloud upsampling using graph convolutional networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 11683–11692.
  31. PUGeo-Net: A geometry-centric network for 3D point cloud upsampling. In European conference on computer vision, 752–769. Springer.
  32. Deep magnification-flexible upsampling over 3d point clouds. IEEE Transactions on Image Processing, 30: 8354–8367.
  33. Qiu, S.; et al. 2022. Pu-transformer: Point cloud upsampling transformer. In Proceedings of the Asian Conference on Computer Vision, 2475–2493.
  34. Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data. In Proceedings of the IEEE/CVF international conference on computer vision, 1588–1597.
  35. Deep points consolidation. ACM Transactions on Graphics (ToG), 34(6): 1–13.
  36. Meta-PU: An arbitrary-scale upsampling network for point cloud. IEEE transactions on visualization and computer graphics, 28(9): 3206–3218.
  37. Patch-based progressive 3d point set upsampling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 5958–5967.
  38. Pu-net: Point cloud upsampling network. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2790–2799.
  39. A review of deep learning-based semantic segmentation for point cloud. IEEE access, 7: 179118–179133.
  40. Fast learning radiance fields by shooting much fewer rays. IEEE Transactions on Image Processing.
  41. Self-Supervised Arbitrary-Scale Implicit Point Clouds Upsampling. IEEE Transactions on Pattern Analysis and Machine Intelligence.
  42. Self-supervised arbitrary-scale point clouds upsampling via implicit neural representation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999–2007.
  43. Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection. In Proceedings of the IEEE/CVF international conference on computer vision.
  44. Learning consistency-aware unsigned distance functions progressively from raw point clouds. Advances in Neural Information Processing Systems, 35: 16481–16494.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Shujuan Li (7 papers)
  2. Junsheng Zhou (28 papers)
  3. Baorui Ma (18 papers)
  4. Yu-Shen Liu (79 papers)
  5. Zhizhong Han (73 papers)
Citations (16)
View on Semantic Scholar

Summary

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

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