Enhancing Diffusion-based Point Cloud Generation with Smoothness Constraint

• URL: http://arxiv.org/abs/2404.02396v1
• Date: Wed, 3 Apr 2024 01:55:15 GMT
• Title: Enhancing Diffusion-based Point Cloud Generation with Smoothness Constraint
• Authors: Yukun Li, Liping Liu,
• Abstract summary: Diffusion models have been popular for point cloud generation tasks. We propose 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.
• Score: 5.140589325829964
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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.

Related papers

• Amortized Posterior Sampling with Diffusion Prior Distillation [55.03585818289934]
  We propose a variational inference approach to sample from the posterior distribution for solving inverse problems. We show that our method is applicable to standard signals in Euclidean space, as well as signals on manifold.
  arXiv  Detail & Related papers  (2024-07-25T09:53:12Z)
• PCRDiffusion: Diffusion Probabilistic Models for Point Cloud Registration [28.633279452622475]
  We propose a new framework that formulates point cloud registration as a denoising diffusion process from noisy transformation to object transformation. During training stage, object transformation diffuses from ground-truth transformation to random distribution, and the model learns to reverse this noising process. In sampling stage, the model refines randomly generated transformation to the output result in a progressive way.
  arXiv  Detail & Related papers  (2023-12-11T01:56:42Z)
• A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling [10.390581335119098]
  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.
  arXiv  Detail & Related papers  (2023-12-03T12:41:41Z)
• To smooth a cloud or to pin it down: Guarantees and Insights on Score Matching in Denoising Diffusion Models [20.315727650065007]
  Denoising diffusion models are a class of generative models which have recently achieved state-of-the-art results across many domains. We leverage known connections to control akin to the F"ollmer drift to extend established neural network approximation results for the F"ollmer drift to denoising diffusion models and samplers.
  arXiv  Detail & Related papers  (2023-05-16T16:56:19Z)
• A Variational Perspective on Solving Inverse Problems with Diffusion Models [101.831766524264]
  Inverse tasks can be formulated as inferring a posterior distribution over data. This is however challenging in diffusion models since the nonlinear and iterative nature of the diffusion process renders the posterior intractable. We propose a variational approach that by design seeks to approximate the true posterior distribution.
  arXiv  Detail & Related papers  (2023-05-07T23:00:47Z)
• 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)
• ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories [144.03939123870416]
  We propose a novel conditional diffusion model by introducing conditions into the forward process. We use extra latent space to allocate an exclusive diffusion trajectory for each condition based on some shifting rules. We formulate our method, which we call textbfShiftDDPMs, and provide a unified point of view on existing related methods.
  arXiv  Detail & Related papers  (2023-02-05T12:48:21Z)
• ManiFlow: Implicitly Representing Manifolds with Normalizing Flows [145.9820993054072]
  Normalizing Flows (NFs) are flexible explicit generative models that have been shown to accurately model complex real-world data distributions. We propose an optimization objective that recovers the most likely point on the manifold given a sample from the perturbed distribution. Finally, we focus on 3D point clouds for which we utilize the explicit nature of NFs, i.e. surface normals extracted from the gradient of the log-likelihood and the log-likelihood itself.
  arXiv  Detail & Related papers  (2022-08-18T16:07:59Z)
• Diffusion Probabilistic Models for 3D Point Cloud Generation [12.257593992442732]
  We present a probabilistic model for point cloud generation that is critical for various 3D vision tasks. Inspired by the diffusion process in non-equilibrium thermodynamics, we view points in point clouds as particles in a thermodynamic system in contact with a heat bath. We derive the variational bound in closed form for training and provide implementations of the model.
  arXiv  Detail & Related papers  (2021-03-02T03:56:02Z)
• Learning Gradient Fields for Shape Generation [69.85355757242075]
  A point cloud can be viewed as samples from a distribution of 3D points whose density is concentrated near the surface of the shape. We generate point clouds by performing gradient ascent on an unnormalized probability density. Our model directly predicts the gradient of the log density field and can be trained with a simple objective adapted from score-based generative models.
  arXiv  Detail & Related papers  (2020-08-14T18:06:15Z)

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.