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

A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling (2312.02719v1)

Published 3 Dec 2023 in cs.CV

Abstract: Point cloud upsampling (PCU) enriches the representation of raw point clouds, significantly improving the performance in downstream tasks such as classification and reconstruction. Most of the existing point cloud upsampling methods focus on sparse point cloud feature extraction and upsampling module design. In a different way, we dive deeper into directly modelling the gradient of data distribution from dense point clouds. In this paper, we proposed a conditional denoising diffusion probability model (DDPM) for point cloud upsampling, called PUDM. Specifically, PUDM treats the sparse point cloud as a condition, and iteratively learns the transformation relationship between the dense point cloud and the noise. Simultaneously, PUDM aligns with a dual mapping paradigm to further improve the discernment of point features. In this context, PUDM enables learning complex geometry details in the ground truth through the dominant features, while avoiding an additional upsampling module design. Furthermore, to generate high-quality arbitrary-scale point clouds during inference, PUDM exploits the prior knowledge of the scale between sparse point clouds and dense point clouds during training by parameterizing a rate factor. Moreover, PUDM exhibits strong noise robustness in experimental results. In the quantitative and qualitative evaluations on PU1K and PUGAN, PUDM significantly outperformed existing methods in terms of Chamfer Distance (CD) and Hausdorff Distance (HD), achieving state of the art (SOTA) performance.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012, 2015.
  2. 4d spatio-temporal convnets: Minkowski convolutional neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 3075–3084, 2019a.
  3. Fully convolutional geometric features. In Proceedings of the IEEE/CVF international conference on computer vision, pages 8958–8966, 2019b.
  4. Deep learning for image and point cloud fusion in autonomous driving: A review. pages 722–739. IEEE, 2021.
  5. Scannet: Richly-annotated 3d reconstructions of indoor scenes. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5828–5839, 2017.
  6. Diffusion models beat gans on image synthesis. Advances in neural information processing systems, 34:8780–8794, 2021.
  7. Neural points: Point cloud representation with neural fields for arbitrary upsampling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 18633–18642, 2022.
  8. Vision meets robotics: The kitti dataset. pages 1231–1237. Sage Publications Sage UK: London, England, 2013.
  9. 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, pages 5354–5363, 2023.
  10. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598, 2022.
  11. Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840–6851, 2020.
  12. Predator: Registration of 3d point clouds with low overlap. In Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition, pages 4267–4276, 2021.
  13. Spovt: Semantic-prototype variational transformer for dense point cloud semantic completion. Advances in Neural Information Processing Systems, 35:33934–33946, 2022a.
  14. Frozen clip model is efficient point cloud backbone. arXiv preprint arXiv:2212.04098, 2022b.
  15. Imfnet: Interpretable multimodal fusion for point cloud registration. IEEE Robotics and Automation Letters, 7(4):12323–12330, 2022c.
  16. Deepi2p: Image-to-point cloud registration via deep classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15960–15969, 2021.
  17. Pu-gan: a point cloud upsampling adversarial network. In Proceedings of the IEEE/CVF international conference on computer vision, pages 7203–7212, 2019.
  18. Point cloud upsampling via disentangled refinement. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 344–353, 2021.
  19. Learning efficient point cloud generation for dense 3d object reconstruction. In proceedings of the AAAI Conference on Artificial Intelligence, 2018.
  20. Weaklabel3d-net: A complete framework for real-scene lidar point clouds weakly supervised multi-tasks understanding. In 2022 international conference on robotics and automation (ICRA), pages 5108–5115. IEEE, 2022.
  21. Point-voxel cnn for efficient 3d deep learning. Advances in Neural Information Processing Systems, 32, 2019.
  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, pages 16208–16217, 2021.
  23. Diffusion probabilistic models for 3d point cloud generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2837–2845, 2021.
  24. A conditional point diffusion-refinement paradigm for 3d point cloud completion. arXiv preprint arXiv:2112.03530, 2021.
  25. Pc2: Projection-conditioned point cloud diffusion for single-image 3d reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12923–12932, 2023.
  26. Variational relational point completion network. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8524–8533, 2021.
  27. Scalable diffusion models with transformers. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4195–4205, 2023.
  28. Dgcnn: A convolutional neural network over large-scale labeled graphs. Neural Networks, 108:533–543, 2018.
  29. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 652–660, 2017a.
  30. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 30, 2017b.
  31. Pu-gcn: Point cloud upsampling using graph convolutional networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11683–11692, 2021.
  32. Pix4point: Image pretrained transformers for 3d point cloud understanding. 2022.
  33. Pugeo-net: A geometry-centric network for 3d point cloud upsampling. In European conference on computer vision, pages 752–769. Springer, 2020.
  34. Zero-shot text-to-image generation. In International Conference on Machine Learning, pages 8821–8831. PMLR, 2021.
  35. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 1(2):3, 2022.
  36. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10684–10695, 2022.
  37. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, 35:36479–36494, 2022.
  38. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502, 2020a.
  39. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456, 2020b.
  40. Kpconv: Flexible and deformable convolution for point clouds. In Proceedings of the IEEE/CVF international conference on computer vision, pages 6411–6420, 2019.
  41. Balanced chamfer distance as a comprehensive metric for point cloud completion. Advances in Neural Information Processing Systems, 34:29088–29100, 2021.
  42. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1912–1920, 2015.
  43. Dream3d: Zero-shot text-to-3d synthesis using 3d shape prior and text-to-image diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 20908–20918, 2023.
  44. A novel system for off-line 3d seam extraction and path planning based on point cloud segmentation for arc welding robot. Robotics and Computer-Integrated Manufacturing, 64:101929, 2020.
  45. Patch-based progressive 3d point set upsampling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5958–5967, 2019.
  46. Pu-net: Point cloud upsampling network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2790–2799, 2018.
  47. Cem Yuksel. Sample elimination for generating poisson disk sample sets. In Computer Graphics Forum, pages 25–32. Wiley Online Library, 2015.
  48. Pointclip: Point cloud understanding by clip. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8552–8562, 2022.
  49. Point transformer. In Proceedings of the IEEE/CVF international conference on computer vision, pages 16259–16268, 2021.
  50. Global-pbnet: A novel point cloud registration for autonomous driving. pages 22312–22319. IEEE, 2022.
  51. 3d shape generation and completion through point-voxel diffusion. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 5826–5835, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Wentao Qu (6 papers)
  2. Yuantian Shao (1 paper)
  3. Lingwu Meng (1 paper)
  4. Xiaoshui Huang (55 papers)
  5. Liang Xiao (80 papers)
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