Feature-preserving simplification framework for 3D point cloud

Xu, Xueli; Li, Kang; Ma, Yan; Geng, Guohua; Wang, Jingyu; Zhou, Mingquan; Cao, Xin

doi:10.1038/s41598-022-13550-1

“…To improve accuracy in determining risk level, we use closeness to measure the degree of fit between the comprehensive risk cloud map and the standard cloud map. The larger the closeness value, the closer the comprehensive risk cloud is to the corresponding standard cloud level 52 . The formula for calculating closeness is as follows:…”

Section: W W W Ex En Hementioning

confidence: 99%

Risk Assessment of Equipment Research Project Costs Based on FAHP-CRITIC Combined Weights for 2D Cloud Models

Zhu,

Sun,

Chen

et al. 2024

Preprint

1

0

View full text Add to dashboard Cite

The development process of equipment research projects is fraught with uncertainties, making it challenging to provide an accurate and objective evaluation of their development costs. To enhance the accuracy of cost prediction for equipment research projects, it is essential to consider the cost risk level and conduct relevant research on cost risk assessment. This study proposes an improved two-dimensional cloud model that integrates qualitative concepts and quantitative data for researching equipment projects. An assessment index system is constructed with three primary indicators and twelve secondary indicators. The main factors affecting the cost are comprehensively considered. The probability of overspending and the degree of impact of overspending are taken as the basic variables for assessing each indicator according to the definition of cost risk. The study combined the Fuzzy Analytic Hierarchy Process (FAHP) method with the Criteria Importance Though Intercrieria Correlation (CRITIC) method using the cooperative game method to determine the weights of each assessment indicator. Subsequently, a two-dimensional cloud model was established to obtain the cloud eigenvalues. A two-dimensional cloud diagram was drawn through MATLAB to initially determine the risk level, and the closeness was calculated to accurately determine the results. Finally, using a specific anti-mine system as an example, we verified the validity and feasibility of the model by comparing it with the traditional method. The results demonstrate that the improved two-dimensional cloud model can overcome the ambiguity and randomness of data in cost risk assessment and can provide a reference for other scientific research projects of the same type.

show abstract

“…Point cloud completion, which aims to recover the complete shapes from incomplete point clouds 6 , has attracted lots of interest since the high-quality reconstruction of complete shapes is always essential for the tasks of point cloud recognition 7 , point cloud simplification 8 , scene segmentation 9 and 3d reconstruction 10 , etc. The traditional point completion network (PCN) 11 employed a simple encoder–decoder framework to generate the complete shapes from incomplete point cloud data, and adopted FoldingNet operation for mapping 2d grid to 3d surfaces by mimicking the planar folding deformation 12 .…”

Section: Introductionmentioning

confidence: 99%

A coarse-to-fine point completion network with details compensation and structure enhancement

Miao,

Jing,

Gao

et al. 2024

Sci Rep

0

View full text Add to dashboard Cite

Point cloud completion, the issue of estimating the complete geometry of objects from partially-scanned point cloud data, becomes a fundamental task in many 3d vision and robotics applications. To address the limitations on inadequate prediction of shape details for traditional methods, a novel coarse-to-fine point completion network (DCSE-PCN) is introduced in this work using the modules of local details compensation and shape structure enhancement for effective geometric learning. The coarse completion stage of our network consists of two branches—a shape structure recovery branch and a local details compensation branch, which can recover the overall shape of the underlying model and the shape details of incomplete point cloud through feature learning and hierarchical feature fusion. The fine completion stage of our network employs the structure enhancement module to reinforce the correlated shape structures of the coarse repaired shape (such as regular arrangement or symmetry), thus obtaining the completed geometric shape with finer-grained details. Extensive experimental results on ShapeNet dataset and ModelNet dataset validate the effectiveness of our completion network, which can recover the shape details of the underlying point cloud whilst maintaining its overall shape. Compared to the existing methods, our coarse-to-fine completion network has shown its competitive performance on both chamfer distance (CD) and earth mover distance (EMD) errors. Such as, the repairing results on the ShapeNet dataset of our completion network are reduced by an average of $$35.62\%$$ 35.62 % , $$33.31\%$$ 33.31 % , $$29.62\%$$ 29.62 % , and $$23.62\%$$ 23.62 % in terms of CD error, comparing with PCN, FoldingNet, Atlas, and CRN methods, respectively; and also reduced by an average of $$15.63\%$$ 15.63 % , $$1.29\%$$ 1.29 % , $$64.52\%$$ 64.52 % , and $$62.87\%$$ 62.87 % in terms of EMD error, respectively. Meanwhile, the completion results on the ModelNet dataset of our network have an average reduction of $$28.41\%$$ 28.41 % , $$26.57\%$$ 26.57 % , $$20.65\%$$ 20.65 % , and $$18.55\%$$ 18.55 % in terms of CD error, comparing to PCN, FoldingNet, Atlas, and CRN methods, respectively; and also an average reduction of $$21.91\%$$ 21.91 % , $$19.59\%$$ 19.59 % , $$43.51\%$$ 43.51 % , and $$21.49\%$$ 21.49 % in terms of EMD error, respectively. Our proposed point completion network is also robust to different degrees of data incompleteness and model noise.

show abstract

“…Feature-preserving point cloud refinement methods have become a hot topic in current research [13,14]. The selection of feature points is mainly determined by parameters such as normals and curvatures [7].…”

Section: Introductionmentioning

confidence: 99%

A Tree Point Cloud Simplification Method Based on FPFH Information Entropy

Hu

¹

,

Yu

²

,

Fang

³

et al. 2023

Forests

View full text Add to dashboard Cite

LiDAR technology has been widely used in forest survey and research, but the high-resolution point cloud data generated by LiDAR equipment also pose challenges in storage and computing. To address this problem, we propose a point cloud simplification method for trees, which considers both higher similarity to the original point cloud and the area of the tree point cloud. The method first determines the optimal search neighborhood using the standard deviation of FPFH information entropy. Based on FPFH information entropy and Poisson disc sampling theory, the point cloud is partitioned and sampled. By optimizing the separation thresholds of significant feature points and less significant feature points using a genetic algorithm with the Hausdorff distance and point cloud area as the objective function, the final simplified point cloud is obtained. Validation with two point cloud data sets shows that the proposed method achieves good retention of the area information of the original point cloud while ensuring point cloud quality. The research provides new approaches and techniques for processing large-scale forest LiDAR scan point clouds, reducing storage and computing requirements. This can improve the efficiency of forest surveys and monitoring.

show abstract

Feature-preserving simplification framework for 3D point cloud

Cited by 13 publications

References 33 publications

Risk Assessment of Equipment Research Project Costs Based on FAHP-CRITIC Combined Weights for 2D Cloud Models

Risk Assessment of Equipment Research Project Costs Based on FAHP-CRITIC Combined Weights for 2D Cloud Models

A coarse-to-fine point completion network with details compensation and structure enhancement

A Tree Point Cloud Simplification Method Based on FPFH Information Entropy

Contact Info

Product

Resources

About