Edge Preserving Implicit Surface Representation of Point Clouds

• URL: http://arxiv.org/abs/2301.04860v1
• Date: Thu, 12 Jan 2023 08:04:47 GMT
• Title: Edge Preserving Implicit Surface Representation of Point Clouds
• Authors: Xiaogang Wang, Yuhang Cheng, Liang Wang, Jiangbo Lu, Kai Xu, Guoqiang Xiao
• Abstract summary: We propose a novel edge-preserving implicit surface reconstruction method, which mainly consists of a differentiable Laplican regularizer and a dynamic edge sampling strategy. Compared with the state-of-the-art methods, experimental results show that our method significantly improves the quality of 3D reconstruction results.
• Score: 27.632399836710164
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning implicit surface directly from raw data recently has become a very attractive representation method for 3D reconstruction tasks due to its excellent performance. However, as the raw data quality deteriorates, the implicit functions often lead to unsatisfactory reconstruction results. To this end, we propose a novel edge-preserving implicit surface reconstruction method, which mainly consists of a differentiable Laplican regularizer and a dynamic edge sampling strategy. Among them, the differential Laplican regularizer can effectively alleviate the implicit surface unsmoothness caused by the point cloud quality deteriorates; Meanwhile, in order to reduce the excessive smoothing at the edge regions of implicit suface, we proposed a dynamic edge extract strategy for sampling near the sharp edge of point cloud, which can effectively avoid the Laplacian regularizer from smoothing all regions. Finally, we combine them with a simple regularization term for robust implicit surface reconstruction. Compared with the state-of-the-art methods, experimental results show that our method significantly improves the quality of 3D reconstruction results. Moreover, we demonstrate through several experiments that our method can be conveniently and effectively applied to some point cloud analysis tasks, including point cloud edge feature extraction, normal estimation,etc.

Related papers

• MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Step [48.812388649469106]
  We propose a novel method to learn multi-scale implicit fields from raw point clouds by optimizing accurate SDFs from coarse to fine. Our experiments on widely used object and scene benchmarks demonstrate that our method outperforms the state-of-the-art methods in surface reconstruction.
  arXiv  Detail & Related papers  (2024-11-02T10:50:22Z)
• ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction [50.07671826433922]
  It is non-trivial to simultaneously recover meticulous geometry and preserve smoothness across regions with differing characteristics. We propose ND-SDF, which learns a Normal Deflection field to represent the angular deviation between the scene normal and the prior normal. Our method not only obtains smooth weakly textured regions such as walls and floors but also preserves the geometric details of complex structures.
  arXiv  Detail & Related papers  (2024-08-22T17:59:01Z)
• MergeNet: Explicit Mesh Reconstruction from Sparse Point Clouds via Edge Prediction [11.280646720745729]
  Existing implicit methods produce superior smooth and watertight meshes. Explicit methods are more efficient by directly forming the face from points. We propose MEshMerge Reconstruction via edGE(Net), which converts mesh reconstruction into local connectivity prediction problems.
  arXiv  Detail & Related papers  (2024-07-16T11:19:16Z)
• Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning [52.825441454264585]
  We propose an arbitrary-scale Point cloud Upsampling framework using Voxel-based Network (textbfPU-VoxelNet) Thanks to the completeness and regularity inherited from the voxel representation, voxel-based networks are capable of providing predefined grid space to approximate 3D surface. A density-guided grid resampling method is developed to generate high-fidelity points while effectively avoiding sampling outliers.
  arXiv  Detail & Related papers  (2024-03-08T07:31:14Z)
• Indoor Scene Reconstruction with Fine-Grained Details Using Hybrid Representation and Normal Prior Enhancement [50.56517624931987]
  The reconstruction of indoor scenes from multi-view RGB images is challenging due to the coexistence of flat and texture-less regions. Recent methods leverage neural radiance fields aided by predicted surface normal priors to recover the scene geometry. This work aims to reconstruct high-fidelity surfaces with fine-grained details by addressing the above limitations.
  arXiv  Detail & Related papers  (2023-09-14T12:05:29Z)
• Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessian [44.28251558359345]
  We propose a new approach for reconstructing surfaces from point clouds. Our technique aligns the gradients for a near-surface point and its on-surface projection point, producing a rough but faithful shape within just a few iterations.
  arXiv  Detail & Related papers  (2023-09-04T20:10:38Z)
• Domain Reduction Strategy for Non Line of Sight Imaging [20.473142941237015]
  In non-line-of-sight (NLOS) imaging, the visible surfaces of the target objects are notably sparse. We design our method to render the transients through partial propagations from a continuously sampled set of points from the hidden space. Our method is capable of accurately and efficiently modeling the view-dependent reflectance using surface normals.
  arXiv  Detail & Related papers  (2023-08-20T14:00:33Z)
• Enhancing Surface Neural Implicits with Curvature-Guided Sampling and Uncertainty-Augmented Representations [37.42624848693373]
  We introduce a method that directly digests depth images for the task of high-fidelity 3D reconstruction. A simple sampling strategy is proposed to generate highly effective training data. Despite its simplicity, our method outperforms a range of both classical and learning-based baselines.
  arXiv  Detail & Related papers  (2023-06-03T12:23:17Z)
• NeuralMeshing: Differentiable Meshing of Implicit Neural Representations [63.18340058854517]
  We propose a novel differentiable meshing algorithm for extracting surface meshes from neural implicit representations. Our method produces meshes with regular tessellation patterns and fewer triangle faces compared to existing methods.
  arXiv  Detail & Related papers  (2022-10-05T16:52:25Z)
• Differentiable Surface Rendering via Non-Differentiable Sampling [19.606523934811577]
  We present a method for differentiable rendering of 3D surfaces that supports both explicit and implicit representations. We show for the first time efficient, differentiable rendering of an iso extracted from a neural radiance field (NeRF), and demonstrate surface-based, rather than volume-based, rendering of a NeRF.
  arXiv  Detail & Related papers  (2021-08-10T19:25:06Z)
• Shape As Points: A Differentiable Poisson Solver [118.12466580918172]
  In this paper, we introduce a differentiable point-to-mesh layer using a differentiable formulation of Poisson Surface Reconstruction (PSR) The differentiable PSR layer allows us to efficiently and differentiably bridge the explicit 3D point representation with the 3D mesh via the implicit indicator field. Compared to neural implicit representations, our Shape-As-Points (SAP) model is more interpretable, lightweight, and accelerates inference time by one order of magnitude.
  arXiv  Detail & Related papers  (2021-06-07T09:28:38Z)

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.