A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling

• URL: http://arxiv.org/abs/2312.02719v1
• Date: Sun, 3 Dec 2023 12:41:41 GMT
• Title: A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling
• Authors: Wentao Qu, Yuantian Shao, Lingwu Meng, Xiaoshui Huang, Liang Xiao
• Abstract summary: We propose a conditional denoising diffusion probability model (DDPM) for point cloud upsampling, called PUDM. PUDM treats the sparse point cloud as a condition, and iteratively learns the transformation relationship between the dense point cloud and the noise. PUDM exhibits strong noise robustness in experimental results.
• Score: 10.390581335119098
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Point Cloud Pre-training with Diffusion Models [62.12279263217138]
  We propose a novel pre-training method called Point cloud Diffusion pre-training (PointDif) PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification, segmentation and detection.
  arXiv  Detail & Related papers  (2023-11-25T08:10:05Z)
• Controllable Mesh Generation Through Sparse Latent Point Diffusion Models [105.83595545314334]
  We design a novel sparse latent point diffusion model for mesh generation. Our key insight is to regard point clouds as an intermediate representation of meshes, and model the distribution of point clouds instead. Our proposed sparse latent point diffusion model achieves superior performance in terms of generation quality and controllability.
  arXiv  Detail & Related papers  (2023-03-14T14:25:29Z)
• Joint Geometry and Attribute Upsampling of Point Clouds Using Frequency-Selective Models with Overlapped Support [4.211128681972148]
  We propose Frequency-Selective Upsampling (FSU), an upsampling scheme that upsamples geometry and attribute information of point clouds jointly. We show best performances for our proposed FSU in terms of point-to-plane error and plane-to-plane angular similarity.
  arXiv  Detail & Related papers  (2023-01-27T10:20:06Z)
• PU-MFA : Point Cloud Up-sampling via Multi-scale Features Attention [0.0]
  This paper proposes a new point cloud up-sampling method called Point cloud Up-sampling via Multi-scale Features Attention (PU-MFA) PU-MFA shows superior performance in quantitative and qualitative evaluation compared to other state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-08-22T02:53:05Z)
• BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling [60.257912103351394]
  We develop a new point cloud upsampling pipeline called BIMS-PU. We decompose the up/downsampling procedure into several up/downsampling sub-steps by breaking the target sampling factor into smaller factors. We show that our method achieves superior results to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-06-25T13:13:37Z)
• Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation [79.60988242843437]
  We propose a novel approach that achieves self-supervised and magnification-flexible point clouds upsampling simultaneously. Experimental results demonstrate that our self-supervised learning based scheme achieves competitive or even better performance than supervised learning based state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-18T07:18:25Z)
• A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion [69.32451612060214]
  Real-scanned 3D point clouds are often incomplete, and it is important to recover complete point clouds for downstream applications. Most existing point cloud completion methods use Chamfer Distance (CD) loss for training. We propose a novel Point Diffusion-Refinement (PDR) paradigm for point cloud completion.
  arXiv  Detail & Related papers  (2021-12-07T06:59:06Z)
• Deep Point Set Resampling via Gradient Fields [11.5128379063303]
  3D point clouds acquired by scanning real-world objects or scenes have found a wide range of applications. They are often perturbed by noise or suffer from low density, which obstructs downstream tasks such as surface reconstruction and understanding. We propose a novel paradigm of point set resampling for restoration, which learns continuous gradient fields of point clouds.
  arXiv  Detail & Related papers  (2021-11-03T07:20:35Z)
• PU-Flow: a Point Cloud Upsampling Networkwith Normalizing Flows [58.96306192736593]
  We present PU-Flow, which incorporates normalizing flows and feature techniques to produce dense points uniformly distributed on the underlying surface. Specifically, we formulate the upsampling process as point in a latent space, where the weights are adaptively learned from local geometric context. We show that our method outperforms state-of-the-art deep learning-based approaches in terms of reconstruction quality, proximity-to-surface accuracy, and computation efficiency.
  arXiv  Detail & Related papers  (2021-07-13T07:45:48Z)
• "Zero Shot" Point Cloud Upsampling [4.737519767218666]
  We present an unsupervised approach to upsample point clouds internally referred as "Zero Shot" Point Cloud Upsampling (ZSPU) at holistic level. Our approach is solely based on the internal information provided by a particular point cloud without patching in both self-training and testing phases. ZSPU achieves superior qualitative results on shapes with complex local details or high curvatures.
  arXiv  Detail & Related papers  (2021-06-25T17:06:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.