# Surface Reconstruction from Point Clouds: A Survey and a Benchmark

arXiv: https://arxiv.org/abs/2205.02413 · HTML: https://mlsanity.com/paper/2205.02413/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 72 of its 153 references that are in the map.
- First posted on arXiv 5 May 2022.

## Builds on (most cited first, 30 of 72)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://mlsanity.com/paper/1804.01654/) (2018)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [Neural 3D Mesh Renderer](https://mlsanity.com/paper/1711.07566/) (2017)
- [Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes](https://mlsanity.com/paper/2101.10994/) (2021)
- [SAL: Sign Agnostic Learning of Shapes from Raw Data](https://mlsanity.com/paper/1911.10414/) (2019)
- [3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics](https://mlsanity.com/paper/2011.09127/) (2020)
- [Local Implicit Grid Representations for 3D Scenes](https://mlsanity.com/paper/2003.08981/) (2020)
- [Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion](https://mlsanity.com/paper/2003.01456/) (2020)
- [ABC: A Big CAD Model Dataset For Geometric Deep Learning](https://mlsanity.com/paper/1812.06216/) (2018)
- [Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction](https://mlsanity.com/paper/2003.10983/) (2020)
- [Neural Unsigned Distance Fields for Implicit Function Learning](https://mlsanity.com/paper/2010.13938/) (2020)
- [Shape As Points: A Differentiable Poisson Solver](https://mlsanity.com/paper/2106.03452/) (2021)
- [Thingi10K: A Dataset of 10,000 3D-Printing Models](https://mlsanity.com/paper/1605.04797/) (2016)
- [Tangent Convolutions for Dense Prediction in 3D](https://mlsanity.com/paper/1807.02443/) (2018)
- [Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces](https://mlsanity.com/paper/2011.13495/) (2020)

## Built on by (most cited first, 30 of 41)

- [Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessian](https://mlsanity.com/paper/2309.01793/) (2023)
- [3D Scene Generation: A Survey](https://mlsanity.com/paper/2505.05474/) (2025)
- [HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes with Iterative Intertwined Regularization](https://mlsanity.com/paper/2302.14340/) (2023)
- [VisCo Grids: Surface Reconstruction with Viscosity and Coarea Grids](https://mlsanity.com/paper/2303.14569/) (2023)
- [PoNQ: a Neural QEM-based Mesh Representation](https://mlsanity.com/paper/2403.12870/) (2024)
- [3D Reconstruction with Fast Dipole Sums](https://mlsanity.com/paper/2405.16788/) (2024)
- [A Survey and Benchmark of Automatic Surface Reconstruction from Point Clouds](https://mlsanity.com/paper/2301.13656/) (2023)
- [Point normal orientation and surface reconstruction by incorporating isovalue constraints to Poisson equation](https://mlsanity.com/paper/2209.15619/) (2022)
- [Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Clouds](https://mlsanity.com/paper/2410.18477/) (2024)
- [Parametric Point Cloud Completion for Polygonal Surface Reconstruction](https://mlsanity.com/paper/2503.08363/) (2025)
- [Is Single-View Mesh Reconstruction Ready for Robotics?](https://mlsanity.com/paper/2505.17966/) (2025)
- [MICAS: Multi-grained In-Context Adaptive Sampling for 3D Point Cloud Processing](https://mlsanity.com/paper/2411.16773/) (2024)
- [Free-T2M: Robust Text-to-Motion Generation for Humanoid Robots via Frequency-Domain](https://mlsanity.com/paper/2501.18232/) (2025)
- [Procedural Generation of 3D Maize Plant Architecture from LIDAR Data](https://mlsanity.com/paper/2501.13963/) (2025)
- [Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks](https://mlsanity.com/paper/2508.19071/) (2025)
- [Cutting-edge 3D reconstruction solutions for underwater coral reef images: A review and comparison](https://mlsanity.com/paper/2502.20154/) (2025)
- [Rethinking Metrics and Diffusion Architecture for 3D Point Cloud Generation](https://mlsanity.com/paper/2511.05308/) (2025)
- [Principal subbundles for dimension reduction](https://mlsanity.com/paper/2307.03128/) (2023)
- [P2CADNet: An End-to-End Reconstruction Network for Parametric 3D CAD Model from Point Clouds](https://mlsanity.com/paper/2310.02638/) (2023)
- [PRS: Sharp Feature Priors for Resolution-Free Surface Remeshing](https://mlsanity.com/paper/2311.18494/) (2023)
- [Incorporating Inductive Biases to Energy-based Generative Models](https://mlsanity.com/paper/2505.01111/) (2025)
- [Deep Learning For Point Cloud Denoising: A Survey](https://mlsanity.com/paper/2508.11932/) (2025)
- [HeartFormer: Semantic-Aware Dual-Structure Transformers for 3D Four-Chamber Cardiac Point Cloud Reconstruction](https://mlsanity.com/paper/2512.00264/) (2025)
- [Meltdown: Circuits and Bifurcations in Point-Cloud-Conditioned 3D Diffusion Transformers](https://mlsanity.com/paper/2602.11130/) (2026)
- [Implicit neural representation for change detection](https://mlsanity.com/paper/2307.15428/) (2023)
- [Learning Polynomial Representations of Physical Objects with Application to Certifying Correct Packing Configurations](https://mlsanity.com/paper/2312.06791/) (2023)
- [LISR: Learning Linear 3D Implicit Surface Representation Using Compactly Supported Radial Basis Functions](https://mlsanity.com/paper/2402.07301/) (2024)
- [Topological reconstruction of sampled surfaces via Morse theory](https://mlsanity.com/paper/2405.17257/) (2024)
- [Mat'ern Kernels for Tunable Implicit Surface Reconstruction](https://mlsanity.com/paper/2409.15466/) (2024)
- [IMPLICITSTAINER: Resolution Agnostic Data-Efficient Virtual Staining Using Neural Implicit Functions](https://mlsanity.com/paper/2505.09831/) (2025)

## Abstract (arXiv)

Reconstruction of a continuous surface of two-dimensional manifold from its raw, discrete point cloud observation is a long-standing problem. 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, 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.