PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows

Mao, Aihua; Du, Zihui; Wen, Yu-Hui; Xuan, Jun; Liu, Yong-Jin

doi:10.1007/978-3-031-20062-5_23

Cited by 15 publications

(5 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address this limitation, Score-based Denoising (Score) [8] utilises gradient ascent to guide the denoising process. In recent years, other supervised methods have also been proposed [25][26][27][28].…”

Section: Supervised Learning-based Methodsmentioning

confidence: 99%

“…During training, we followed the noise addition method in Refs. [8,26], i.e., the additive noise is zero-mean Gaussian noise with a standard deviation ranging from 0.5% to 2.0% of each shape's bounding sphere radius. To do so, the clean point cloud must first be normalised into a unit sphere, and then be added with noise Z ∼ D(µ D , σ 2 D ) where D is the objective noise distribution, µ D = 0, and σ D ∈ [0.005, 0.02].…”

Section: Training Datasetmentioning

confidence: 99%

“…It contains point clouds sampled from 20 mesh shapes at 2 resolutions (sparse, 10k points per shape; and dense, 50k points per shape), and has 3 Gaussian noise levels (1%, 2%, and 3% of the bounding sphere's radius) for each resolution. Following prior works [8,26], we ran one denoising iteration for 1% and 2% noise and ran two denoising iterations for 3% noise. We employed two metrics, Chamfer Distance (CD) and Point-tomesh Distance (P2M), to measure the quality of the denoised point clouds.…”

Section: Punet Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Noise4Denoise: Leveraging noise for unsupervised point cloud denoising

Wang,

Liu,

Zhou

et al. 2024

Comp. Visual Media

View full text Add to dashboard Cite

Existing deep learning-based point cloud denoising methods are generally trained in a supervised manner that requires clean data as ground-truth labels. However, in practice, it is not always feasible to obtain clean point clouds. In this paper, we introduce a novel unsupervised point cloud denoising method that eliminates the need to use clean point clouds as groundtruth labels during training. We demonstrate that it is feasible for neural networks to only take noisy point clouds as input, and learn to approximate and restore their clean versions. In particular, we generate two noise levels for the original point clouds, requiring the second noise level to be twice the amount of the first noise level. With this, we can deduce the relationship between the displacement information that recovers the clean surfaces across the two levels of noise, and thus learn the displacement of each noisy point in order to recover the corresponding clean point. Comprehensive experiments demonstrate that our method achieves outstanding denoising results across various datasets with synthetic and real-world noise, obtaining better performance than previous unsupervised methods and competitive performance to current supervised methods.

show abstract

Section: Supervised Learning-based Methodsmentioning

confidence: 99%

Section: Training Datasetmentioning

confidence: 99%

Section: Punet Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Noise4Denoise: Leveraging noise for unsupervised point cloud denoising

Wang,

Liu,

Zhou

et al. 2024

Comp. Visual Media

View full text Add to dashboard Cite

show abstract

“…Its main feature is that it must be trained. Through the analysis from the perspective of signal processing, Mao et al [11] proposed a PD-Flow framework that regards the clean point cloud as the low-frequency part of the signal and the noise as the high-frequency part of the signal. Then, the original signal is encoded and filtered to the highfrequency information to complete the point cloud denoising.…”

Section: Learning-based Point Cloud Filteringmentioning

confidence: 99%

Nonparametric point cloud filter

Sun,

Wang

2023

IET Image Processing

View full text Add to dashboard Cite

This paper proposes a nonparametric point cloud filter to address the issue that existing point cloud filtering methods cannot retain important point cloud features after filtering and often require complex parameter adjustments. Firstly, a nonparametric clustering method is proposed to cluster various features of the point cloud and filter out isolated outliers. Then, the manifold distance truncation method is adopted to remove the outlier cluster generated by the point cloud clustering to complete point cloud filtering. Additionally, the proposed nonparametric clustering algorithm is compared with four of the latest clustering algorithms, including K‐means clustering and OPTICS clustering to verify the rationality of the clustering features. Finally, the filtering results of the nonparametric point cloud filter are compared with those of statistical filtering and two other recently proposed point cloud filters to demonstrate its improved filtering effect and algorithm stability. The experimental results indicate that the proposed nonparametric point cloud filter can achieve better‐filtering results and retain more point cloud features without adjusting parameters.

show abstract

“…It has disadvantages in terms of long computation times, high computing resource demands due to the spectrogram wavelet transform, and limitations in handling specific scenes and complex point cloud data. Mao et al [22] presented a deep learning-based framework called PD-Flow, achieving high-precision denoising through normalised flow and noise separation. This method requires a large amount of training data and computing resources based on the deep learning model.…”

Section: Introductionmentioning

confidence: 99%

Three-Dimensional Point Cloud-Filtering Method Based on Image Segmentation and Absolute Phase Recovery

Zhang

Long

et al. 2023

Electronics

View full text Add to dashboard Cite

In three-dimensional (3D) shape measurement based on fringe projection, various factors can degrade the quality of the point cloud. Existing point cloud filtering methods involve analyzing the geometric relationship between 3D space and point cloud, which poses challenges such as complex calculation and low efficiency. To improve the accuracy and speed of point cloud filtering, this paper proposes a new point cloud filtering method based on image segmentation and the absolute phase for the 3D imaging obtained by fringe projection. Firstly, a two-dimensional (2D) point cloud mapping image is established based on the 3D point cloud obtained from fringe projection. Secondly, threshold segmentation and region growing methods are used to segment the 2D point cloud mapping image, followed by recording and removal of the segmented noise region. Using the relationship between the noise point cloud and the absolute phase noise point in fringe projection, a reference noise-free point is established, and the absolute phase line segment is restored to obtain the absolute phase of the noise-free point. Finally, a new 2D point cloud mapping image is reconstructed in 3D space to obtain a point cloud with noise removed. Experimental results show that the point cloud denoising accuracy calculated by this method can reach up to 99.974%, and the running time is 0.954 s. The proposed method can effectively remove point cloud noise and avoid complex calculations in 3D space. This method can not only remove the noise of the 3D point cloud but also can restore the partly removed noise point cloud into a noise-free 3D point cloud, which can improve the accuracy of the 3D point cloud.

show abstract

PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows

Cited by 15 publications

References 40 publications

Noise4Denoise: Leveraging noise for unsupervised point cloud denoising

Noise4Denoise: Leveraging noise for unsupervised point cloud denoising

Nonparametric point cloud filter

Three-Dimensional Point Cloud-Filtering Method Based on Image Segmentation and Absolute Phase Recovery

Contact Info

Product

Resources

About