A Survey of Surface Reconstruction from Point Clouds

By M. Berger, Andrea Tagliasacchi, Lee M. Seversky, Pierre Alliez, Gaël Guennebaud, Joshua A. Levine, Andrei Sharf, Cláudio T. Silva. Computer graphics forum (Print), 2017

580 citations recorded by the source corpus.

The area of surface reconstruction has seen substantial progress in the past two decades. The traditional problem addressed by surface reconstruction is to recover the digital representation of a physical shape that has been scanned, where the scanned data contain a wide variety of defects. While much of the earlier work has been focused on reconstructing a piece‐wise smooth representation of the original shape, recent work has taken on more specialized priors to address significantly challenging data imperfections, where the reconstruction can take on different representations—not necessarily the explicit geometry. We survey the field of surface reconstruction, and provide a categorization with respect to priors, data imperfections and reconstruction output. By considering a holistic view of surface reconstruction, we show a detailed characterization of the field, highlight similarities between diverse reconstruction techniques and provide directions for future work in surface reconstruction.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Geology

View Paper: https://www.semanticscholar.org/paper/57208db7281f9469ab05888d3fa54d86343c4e27

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Daniel Cohen-Or
2. Olga Sorkine-Hornung
3. P. Heng
4. Chi-Wing Fu
5. Shihao Wu
6. Yaron Lipman
7. Yifan Wang
8. Kang Yin

In Computer Graphics and Computer-Aided Design

1. Daniel Cohen-Or
2. Olga Sorkine-Hornung
3. P. Heng
4. Chi-Wing Fu
5. Shihao Wu
6. Kang Yin
7. Simon Fraser
8. Yifan Wang

In Geology

1. Daniel Cohen-Or
2. P. Heng
3. Chi-Wing Fu
4. Niloy J. Mitra
5. Kang Yin
6. Lequan Yu
7. Simon Fraser
8. Yaron Lipman

Citations in the corpus

• Implicit Geometric Regularization for Learning Shapes (2020, background): “This approach has two drawbacks: First, finding implicit surface representation from raw data is a notoriously hard (and still not solved) problem (Berger et al., 2017); second, decoupling the reconstruction from the learning stage would hinder collective learning and reconstruction of shapes.”
• SAL: Sign Agnostic Learning of Shapes From Raw Data (2019, background): “, a point cloud or a triangle soup(1), no such data is readily available and computing an implicit ground-truth representation for the underlying surface is a notoriously difficult task [5].”
• Differentiable surface splatting for point-based geometry processing (2019, background): “The noise, outliers, incompleteness and misalignments persisting in the raw data pose significant challenges for point cloud filtering, editing, and surface reconstruction [Berger et al. 2017].”
• EC-Net: an Edge-aware Point set Consolidation Network (2018, background): “For a more comprehensive survey, please refer to [13].”
• P2P-NET: Bidirectional Point Displacement Net for Shape Transform (methodology): “…devices, point cloud data is widely captured, accumulated, and processed by many useful techniques, e.g., in point cloud filtering [Mitra and Nguyen 2003], resampling [Huang et al. 2013b], and surface reconstruction [Berger et al. 2017; Carr et al. 2001; Kazhdan and Hoppe 2013], among others.”
• Point convolutional neural networks by extension operators (2018, background): “One important family of bases are the Radial Basis Functions (RBF), that were proven to be useful for surface representation [Berger et al. 2017; Carr et al. 2001].”
• ShapeFormer: Transformer-based Shape Completion via Sparse Representation (2022, background): “This problem of surface completion has been extensively investigated over multiple decades [5].”