2000 character limit reached
Enhancing Diffusion-based Point Cloud Generation with Smoothness Constraint (2404.02396v1)
Published 3 Apr 2024 in cs.CV, cs.GR, and cs.LG
Abstract: Diffusion models have been popular for point cloud generation tasks. Existing works utilize the forward diffusion process to convert the original point distribution into a noise distribution and then learn the reverse diffusion process to recover the point distribution from the noise distribution. However, the reverse diffusion process can produce samples with non-smooth points on the surface because of the ignorance of the point cloud geometric properties. We propose alleviating the problem by incorporating the local smoothness constraint into the diffusion framework for point cloud generation. Experiments demonstrate the proposed model can generate realistic shapes and smoother point clouds, outperforming multiple state-of-the-art methods.
- A lidar point cloud generator: from a virtual world to autonomous driving. In Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, pages 458–464, 2018.
- Interpolated convolutional networks for 3d point cloud understanding. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1578–1587, 2019.
- Randla-net: Efficient semantic segmentation of large-scale point clouds. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11108–11117, 2020.
- Deep learning for 3d point clouds: A survey. IEEE transactions on pattern analysis and machine intelligence, 43(12):4338–4364, 2020.
- A review of point cloud registration algorithms for mobile robotics. Foundations and Trends® in Robotics, 4(1):1–104, 2015.
- A hierarchical spatial transformer for massive point samples in continuous space. arXiv preprint arXiv:2311.04434, 2023.
- Pointcontrast: Unsupervised pre-training for 3d point cloud understanding. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16, pages 574–591. Springer, 2020.
- Curvanet: Geometric deep learning based on directional curvature for 3d shape analysis. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 2214–2224, 2020.
- Pointclip: Point cloud understanding by clip. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8552–8562, 2022.
- Pointweb: Enhancing local neighborhood features for point cloud processing. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5565–5573, 2019.
- Sqn: Weakly-supervised semantic segmentation of large-scale 3d point clouds. In European Conference on Computer Vision, pages 600–619. Springer, 2022.
- Pointflow: 3d point cloud generation with continuous normalizing flows. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4541–4550, 2019.
- 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.
- Learning gradient fields for shape generation. In European Conference on Computer Vision, pages 364–381. Springer, 2020.
- Pointgrow: Autoregressively learned point cloud generation with self-attention. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 61–70, 2020.
- Point cloud gan. arXiv preprint arXiv:1810.05795, 2018.
- 3d point cloud generative adversarial network based on tree structured graph convolutions. In Proceedings of the IEEE/CVF international conference on computer vision, pages 3859–3868, 2019.
- Learning localized generative models for 3d point clouds via graph convolution. In International conference on learning representations, 2018.
- Learning representations and generative models for 3d point clouds. In International conference on machine learning, pages 40–49. PMLR, 2018.
- 3d shape generation and completion through point-voxel diffusion. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 5826–5835, 2021.
- Herbert E Robbins. An empirical bayes approach to statistics. In Breakthroughs in Statistics: Foundations and basic theory, pages 388–394. Springer, 1992.
- Noise2score: tweedie’s approach to self-supervised image denoising without clean images. Advances in Neural Information Processing Systems, 34:864–874, 2021.
- A survey on uncertainty quantification methods for deep neural networks: An uncertainty source perspective. arXiv preprint arXiv:2302.13425, 2023.
- 3d point cloud denoising using graph laplacian regularization of a low dimensional manifold model. IEEE Transactions on Image Processing, 29:3474–3489, 2019.
- Softflow: Probabilistic framework for normalizing flow on manifolds. Advances in Neural Information Processing Systems, 33:16388–16397, 2020.
- Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012, 2015.
- Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456, 2020.
- Score-based generative modeling in latent space. Advances in Neural Information Processing Systems, 34:11287–11302, 2021.
- Nvdiff: Graph generation through the diffusion of node vectors. arXiv preprint arXiv:2211.10794, 2022.
- 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, 2017.
- Occupancy networks: Learning 3d reconstruction in function space. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4460–4470, 2019.