# Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility

arXiv: https://arxiv.org/abs/2108.08378 · HTML: https://mlsanity.com/paper/2108.08378/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 59 references that are in the map.
- First posted on arXiv 18 Aug 2021.

## Builds on (most cited first, 18 of 18)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks](https://mlsanity.com/paper/1911.10127/) (2019)
- [Sparsity Invariant CNNs](https://mlsanity.com/paper/1708.06500/) (2017)
- [Thingi10K: A Dataset of 10,000 3D-Printing Models](https://mlsanity.com/paper/1605.04797/) (2016)
- [Points2Surf: Learning Implicit Surfaces from Point Cloud Patches](https://mlsanity.com/paper/2007.10453/) (2020)
- [Revealing Scenes by Inverting Structure from Motion Reconstructions](https://mlsanity.com/paper/1904.03303/) (2019)
- [Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance](https://mlsanity.com/paper/2007.09267/) (2020)
- [Partial Convolution based Padding](https://mlsanity.com/paper/1811.11718/) (2018)

## Built on by (most cited first, 8 of 8)

- [Deep Surface Reconstruction from Point Clouds with Visibility Information](https://mlsanity.com/paper/2202.01810/) (2022)
- [What's the Situation with Intelligent Mesh Generation: A Survey and Perspectives](https://mlsanity.com/paper/2211.06009/) (2022)
- [Seg-Wild: Interactive Segmentation based on 3D Gaussian Splatting for Unconstrained Image Collections](https://mlsanity.com/paper/2507.07395/) (2025)
- [Joint Point Cloud Upsampling and Cleaning with Octree-based CNNs](https://mlsanity.com/paper/2410.17001/) (2024)
- [Synthetic Data Matters: Re-training with Geo-typical Synthetic Labels for Building Detection](https://mlsanity.com/paper/2507.16657/) (2025)
- [Mesh Conflation of Oblique Photogrammetric Models using Virtual Cameras and Truncated Signed Distance Field](https://mlsanity.com/paper/2308.12139/) (2023)
- [Neural Visibility of Point Sets](https://mlsanity.com/paper/2509.24150/) (2025)
- [Surface Reconstruction from Range Scans Under Visibility Constraints](https://mlsanity.com/paper/2610.18005/) (2026)

## Abstract (arXiv)

We present a novel framework for mesh reconstruction from unstructured point clouds by taking advantage of the learned visibility of the 3D points in the virtual views and traditional graph-cut based mesh generation. Specifically, we first propose a three-step network that explicitly employs depth completion for visibility prediction. Then the visibility information of multiple views is aggregated to generate a 3D mesh model by solving an optimization problem considering visibility in which a novel adaptive visibility weighting in surface determination is also introduced to suppress line of sight with a large incident angle. Compared to other learning-based approaches, our pipeline only exercises the learning on a 2D binary classification task, ie, points visible or not in a view, which is much more generalizable and practically more efficient and capable to deal with a large number of points. Experiments demonstrate that our method with favorable transferability and robustness, and achieve competing performances wrt state-of-the-art learning-based approaches on small complex objects and outperforms on large indoor and outdoor scenes. Code is available at https://github.com/GDAOSU/vis2mesh.