A Survey and Benchmark of Automatic Surface Reconstruction from Point Clouds

• URL: http://arxiv.org/abs/2301.13656v4
• Date: Mon, 02 Dec 2024 12:11:13 GMT
• Title: A Survey and Benchmark of Automatic Surface Reconstruction from Point Clouds
• Authors: Raphael Sulzer, Renaud Marlet, Bruno Vallet, Loic Landrieu,
• Abstract summary: This task is particularly challenging for real-world acquisitions due to factors such as noise, outliers, non-uniform sampling, and missing data. Traditional approaches often simplify the problem by imposing handcrafted priors on either the input point clouds or the resulting surface. Deep learning models have the capability to directly learn the properties of input point clouds and desired surfaces from data.
• Score: 12.58355339505807
• License:
• Abstract: We present a comprehensive survey and benchmark of both traditional and learning-based methods for surface reconstruction from point clouds. This task is particularly challenging for real-world acquisitions due to factors such as noise, outliers, non-uniform sampling, and missing data. Traditional approaches often simplify the problem by imposing handcrafted priors on either the input point clouds or the resulting surface, a process that can require tedious hyperparameter tuning. In contrast, deep learning models have the capability to directly learn the properties of input point clouds and desired surfaces from data. We study the influence of handcrafted and learned priors on the precision and robustness of surface reconstruction techniques. We evaluate various time-tested and contemporary methods in a standardized manner. When both trained and evaluated on point clouds with identical characteristics, the learning-based models consistently produce higher-quality surfaces compared to their traditional counterparts -- even in scenarios involving novel shape categories. However, traditional methods demonstrate greater resilience to the diverse anomalies commonly found in real-world 3D acquisitions. For the benefit of the research community, we make our code and datasets available, inviting further enhancements to learning-based surface reconstruction. This can be accessed at https://github.com/raphaelsulzer/dsr-benchmark .

Related papers

• Machine Learning for Predicting Chaotic Systems [0.0]
  Predicting chaotic dynamical systems is critical in many scientific fields, such as weather forecasting. In this paper, we compare different lightweight and heavyweight machine learning architectures. We introduce the cumulative maximum error, a novel metric that combines desirable properties of traditional metrics and is tailored for chaotic systems.
  arXiv  Detail & Related papers  (2024-07-29T16:34:47Z)
• Flatten Anything: Unsupervised Neural Surface Parameterization [76.4422287292541]
  We introduce the Flatten Anything Model (FAM), an unsupervised neural architecture to achieve global free-boundary surface parameterization. Compared with previous methods, our FAM directly operates on discrete surface points without utilizing connectivity information. Our FAM is fully-automated without the need for pre-cutting and can deal with highly-complex topologies.
  arXiv  Detail & Related papers  (2024-05-23T14:39:52Z)
• Continual Learning with Pre-Trained Models: A Survey [61.97613090666247]
  Continual Learning aims to overcome the catastrophic forgetting of former knowledge when learning new ones. This paper presents a comprehensive survey of the latest advancements in PTM-based CL.
  arXiv  Detail & Related papers  (2024-01-29T18:27:52Z)
• 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)
• HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces [54.77683371400133]
  We propose a novel normal estimation method called HSurf-Net, which can accurately predict normals from point clouds with noise and density variations. Experimental results show that our HSurf-Net achieves the state-of-the-art performance on the synthetic shape dataset.
  arXiv  Detail & Related papers  (2022-10-13T16:39:53Z)
• Surface Reconstruction from Point Clouds: A Survey and a Benchmark [34.78096555134551]
  This paper aims to review and benchmark existing methods in the new era of deep learning surface reconstruction. We contribute a large-scale benchmarking dataset consisting of both synthetic and real-scanned data. We study how different methods generalize in terms of reconstructing complex surface shapes.
  arXiv  Detail & Related papers  (2022-05-05T03:02:57Z)
• Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration [67.69257782645789]
  We propose piecewise transformation fields that learn 3D translation vectors to map any query point in posed space to its correspond position in rest-pose space. We show that fitting parametric models with poses by our network results in much better registration quality, especially for extreme poses.
  arXiv  Detail & Related papers  (2021-04-16T15:16:09Z)
• Model-Based Deep Learning [155.063817656602]
  Signal processing, communications, and control have traditionally relied on classical statistical modeling techniques. Deep neural networks (DNNs) use generic architectures which learn to operate from data, and demonstrate excellent performance. We are interested in hybrid techniques that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches.
  arXiv  Detail & Related papers  (2020-12-15T16:29:49Z)
• Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds [35.80493796701116]
  We propose to learn a local implicit surface network for a shared, adaptive modeling of the entire surface of an object. We also enhance the leveraging of surface self-similarities by improving correlations among the optimized latent codes of individual surface patches. We term our framework as Sign-Agnostic Implicit Learning of Surface Self-Similarities (SAIL-S3)
  arXiv  Detail & Related papers  (2020-12-14T13:33:22Z)
• Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images [64.53227129573293]
  We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views. We design neural networks capable of generating high-quality parametric 3D surfaces which are consistent between views. Our method is supervised and trained on a public dataset of shapes from common object categories.
  arXiv  Detail & Related papers  (2020-08-18T06:33:40Z)
• Points2Surf: Learning Implicit Surfaces from Point Cloud Patches [35.2104818061992]
  A key step in any scanning-based computation is to convert unordered point clouds to a surface. We present Points2Surf, a novel patch-based learning framework that produces accurate surfaces directly from raw scans without normals.
  arXiv  Detail & Related papers  (2020-07-20T20:25:39Z)

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.