Learning modified indicator functions for surface reconstruction

Xiao, Dong; Lin, Siyou; Shi, Zuoqiang; Wang, Bin

doi:10.1016/j.cag.2021.10.017

Cited by 8 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The point clouds are aligned by RGB-D depth images in different time frames, thus enabling digital 3D reconstruction of the vehicle and endowing it with texture information 25 . In the reconstruction of 3D surfaces using neural networks, Sign Agnostic Learning learns implicit representations from point clouds with triangular meshes to achieve surface reconstruction of undirected point clouds 26 ; deep learning networks are introduced to integrate the surface and learn to modify the indicator function parameters from undirected noisy point clouds to generate smooth surfaces with high normal consistency 27 . This restoration method has high approximation capability and high reconstruction accuracy for point cloud surfaces, but it is difficult to converge and has high resource consumption.…”

Section: Related Workmentioning

confidence: 99%

Research on point cloud hole filling and 3D reconstruction in reflective area

Sun,

Miao,

Wang

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Abstract3D reconstruction is the process of obtaining the three-dimensional shape or surface structure of an object, which is widely used in advanced manufacturing fields such as automotive, aerospace, industrial inspection, and reverse engineering. However, due to the structural characteristics of the component itself, the reflective properties of the coating material, and other factors, there may be specular reflection during image acquisition, making it difficult to achieve complete 3D reconstruction of the component. This paper proposes a method to address the problem of incomplete 3D reconstruction of strongly reflective objects by recognizing outlier points and filling point cloud holes. The proposed View-Transform-PointNet outlier point recognition network improves the alignment of the initial point cloud plane and implements secondary alignment of the point cloud based on the perpendicularity between the outlier plane in mixed reflection and the point cloud plane. The point cloud hole-filling method is based on the principle of outlier formation and approximates a local Gaussian distribution to linear variation. The distance between the end of each outlier plane and the real surface is calculated to repair the depth information of outlier points. The proposed method achieves a 39.4% increase in the number of point cloud filling, a 45.2% increase in the number of triangular mesh faces, a 46.9% increase in surface area, and a chamfer distance (CD) of 0.4471009, which is better than existing geometric repair methods in terms of standard deviation and smoothness. The method improves the alignment of initial point cloud planes and enhances the accuracy of outlier point recognition, which are the main innovative points of this study. The 3D reconstruction of the repaired point cloud model is achieved through Poisson equation and parameter adjustment. The proposed method reduces the error caused by large curvature in the boundary region and improves the smoothness and accuracy of the reconstructed model.

show abstract

Section: Related Workmentioning

confidence: 99%

Research on point cloud hole filling and 3D reconstruction in reflective area

Sun,

Miao,

Wang

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In addition to traditional approaches, deep neural networks have been applied to gather information of different scales for orientation and reconstruction (Guerrero et al, 2018;Park et al, 2019;Erler et al, 2020;Xiao et al, 2022;Wang et al, 2022). Among them, Wang et al (2022) utilize local patches for unoriented normal estimation and apply the global features for consistent orientation.…”

Section: Implicit Unoriented Reconstruction and Orientation Based On ...mentioning

confidence: 99%

Point normal orientation and surface reconstruction by incorporating isovalue constraints to Poisson equation

Xiao

Shi

et al. 2023

Computer Aided Geometric Design

Self Cite

View full text Add to dashboard Cite

“…IMLSNet [115] trains an implicit network that evaluates signed distances at grids of an octree-based 3D space, where smoothness is regularized by defining the signed distances in a way similar to implicit moving least-squares [53]. Xiao et al [121] learn a network to implicitly model an indicator function derived from Gauss lemma, which is smooth and linearly approximates the surface; similar to Points2Surf [78], they learn both local and global features.…”

Section: Hybrid Priorsmentioning

confidence: 99%

Surface Reconstruction from Point Clouds: A Survey and a Benchmark

Huang¹,

Wen²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Reconstruction of a continuous surface of two-dimensional manifold from its raw, discrete point cloud observation is a long-standing problem in computer vision and graphics research. The problem is technically ill-posed, and becomes more difficult considering that various sensing imperfections would appear in the point clouds obtained by practical depth scanning. In literature, a rich set of methods has been proposed, and reviews of existing methods are also provided. However, existing reviews are short of thorough investigations on a common benchmark. The present paper aims to review and benchmark existing methods in the new era of deep learning surface reconstruction. To this end, we contribute a large-scale benchmarking dataset consisting of both synthetic and real-scanned data; the benchmark includes object-and scene-level surfaces and takes into account various sensing imperfections that are commonly encountered in practical depth scanning. We conduct thorough empirical studies by comparing existing methods on the constructed benchmark, and pay special attention on robustness of existing methods against various scanning imperfections; we also study how different methods generalize in terms of reconstructing complex surface shapes. Our studies help identify the best conditions under which different methods work, and suggest some empirical findings. For example, while deep learning methods are increasingly popular in the research community, our systematic studies suggest that, surprisingly, a few classical methods perform even better in terms of both robustness and generalization; our studies also suggest that the practical challenges of misalignment of point sets from multi-view scanning, missing of surface points, and point outliers remain unsolved by all the existing surface reconstruction methods. We expect that the benchmark and our studies would be valuable both for practitioners and as a guidance for new innovations in future research. We make the benchmark publicly accessible at https://Gorilla-Lab-SCUT.github.io/SurfaceReconstructionBenchmark.

show abstract

Learning modified indicator functions for surface reconstruction

Cited by 8 publications

References 18 publications

Research on point cloud hole filling and 3D reconstruction in reflective area

Research on point cloud hole filling and 3D reconstruction in reflective area

Point normal orientation and surface reconstruction by incorporating isovalue constraints to Poisson equation

Surface Reconstruction from Point Clouds: A Survey and a Benchmark

Contact Info

Product

Resources

About