Dynamic Point Cloud Denoising via Gradient Fields
- URL: http://arxiv.org/abs/2204.08755v1
- Date: Tue, 19 Apr 2022 08:51:53 GMT
- Title: Dynamic Point Cloud Denoising via Gradient Fields
- Authors: Qianjiang Hu, Wei Hu
- Abstract summary: 3D dynamic point clouds provide a discrete representation of real-world objects or scenes in motion.
Point clouds acquired from sensors are usually perturbed by noise, which affects downstream tasks such as surface reconstruction and analysis.
We propose a novel gradient-field-based dynamic point cloud denoising method, exploiting the temporal correspondence via the estimation of gradient fields.
- Score: 17.29921488701806
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 3D dynamic point clouds provide a discrete representation of real-world
objects or scenes in motion, which have been widely applied in immersive
telepresence, autonomous driving, surveillance, etc. However, point clouds
acquired from sensors are usually perturbed by noise, which affects downstream
tasks such as surface reconstruction and analysis. Although many efforts have
been made for static point cloud denoising, dynamic point cloud denoising
remains under-explored. In this paper, we propose a novel gradient-field-based
dynamic point cloud denoising method, exploiting the temporal correspondence
via the estimation of gradient fields -- a fundamental problem in dynamic point
cloud processing and analysis. The gradient field is the gradient of the
log-probability function of the noisy point cloud, based on which we perform
gradient ascent so as to converge each point to the underlying clean surface.
We estimate the gradient of each surface patch and exploit the temporal
correspondence, where the temporally corresponding patches are searched
leveraging on rigid motion in classical mechanics. In particular, we treat each
patch as a rigid object, which moves in the gradient field of an adjacent frame
via force until reaching a balanced state, i.e., when the sum of gradients over
the patch reaches 0. Since the gradient would be smaller when the point is
closer to the underlying surface, the balanced patch would fit the underlying
surface well, thus leading to the temporal correspondence. Finally, the
position of each point in the patch is updated along the direction of the
gradient averaged from corresponding patches in adjacent frames. Experimental
results demonstrate that the proposed model outperforms state-of-the-art
methods under both synthetic noise and simulated real-world noise.
Related papers
- StraightPCF: Straight Point Cloud Filtering [50.66412286723848]
Point cloud filtering is a fundamental 3D vision task, which aims to remove noise while recovering the underlying clean surfaces.
We introduce StraightPCF, a new deep learning based method for point cloud filtering.
It works by moving noisy points along straight paths, thus reducing discretization errors while ensuring faster convergence to the clean surfaces.
arXiv Detail & Related papers (2024-05-14T05:41:59Z) - Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent
with Learned Distance Functions [77.32043242988738]
We propose a new framework for accurate point cloud upsampling that supports arbitrary upsampling rates.
Our method first interpolates the low-res point cloud according to a given upsampling rate.
arXiv Detail & Related papers (2023-04-24T06:36:35Z) - GECCO: Geometrically-Conditioned Point Diffusion Models [60.28388617034254]
Diffusion models generating images conditionally on text have recently made a splash far beyond the computer vision community.
Here, we tackle the related problem of generating point clouds, both unconditionally, and conditionally with images.
For the latter, we introduce a novel geometrically-motivated conditioning scheme based on projecting sparse image features into the point cloud.
arXiv Detail & Related papers (2023-03-10T13:45:44Z) - PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows [20.382995180671205]
Point cloud denoising aims to restore clean point clouds from raw observations corrupted by noise and outliers.
We present a novel deep learning-based denoising model, that incorporates normalizing flows and noise disentanglement techniques.
arXiv Detail & Related papers (2022-03-11T14:17:58Z) - Shape-invariant 3D Adversarial Point Clouds [111.72163188681807]
Adversary and invisibility are two fundamental but conflict characters of adversarial perturbations.
Previous adversarial attacks on 3D point cloud recognition have often been criticized for their noticeable point outliers.
We propose a novel Point-Cloud Sensitivity Map to boost both the efficiency and imperceptibility of point perturbations.
arXiv Detail & Related papers (2022-03-08T12:21:35Z) - Point Cloud Denoising via Momentum Ascent in Gradient Fields [72.93429911044903]
gradient-based method was proposed to estimate the gradient fields from the noisy point clouds using neural networks.
We develop a momentum gradient ascent method that leverages the information of previous iterations in determining the trajectories of the points.
Experiments demonstrate that the proposed method outperforms state-of-the-art approaches with a variety of point clouds, noise types, and noise levels.
arXiv Detail & Related papers (2022-02-21T10:21:40Z) - Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks [19.703181080679176]
3D dynamic point clouds provide a discrete representation of real-world objects or scenes in motion.
Point clouds acquired from sensors are usually perturbed by noise, which affects downstream tasks such as surface reconstruction and analysis.
We propose a novel gradient-based dynamic point cloud denoising method, exploiting the temporal correspondence for the estimation of gradient fields.
arXiv Detail & Related papers (2022-02-15T09:16:12Z) - 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) - 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) - Dynamic Point Cloud Denoising via Manifold-to-Manifold Distance [24.174744253496513]
We represent dynamic point clouds naturally on spatial-temporal graphs, and exploit the temporal consistency with respect to the underlying surface (manifold)
We formulate dynamic point cloud denoising as the joint optimization of the desired point cloud and underlying graph representation.
Experimental results show that the proposed method significantly outperforms independent denoising of each frame from state-of-the-art static point cloud denoising approaches.
arXiv Detail & Related papers (2020-03-17T04:54:20Z)
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.