# Point2Mesh: A Self-Prior for Deformable Meshes

arXiv: https://arxiv.org/abs/2005.11084 · HTML: https://mlsanity.com/paper/2005.11084/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2020.

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

- [Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors](https://mlsanity.com/paper/2306.17843/) (2023)
- [Text2Mesh: Text-Driven Neural Stylization for Meshes](https://mlsanity.com/paper/2112.03221/) (2021)
- [Neural Kernel Surface Reconstruction](https://mlsanity.com/paper/2305.19590/) (2023)
- [Neural Dual Contouring](https://mlsanity.com/paper/2202.01999/) (2022)
- [Controllable Mesh Generation Through Sparse Latent Point Diffusion Models](https://mlsanity.com/paper/2303.07938/) (2023)
- [Task-Generic Hierarchical Human Motion Prior using VAEs](https://mlsanity.com/paper/2106.04004/) (2021)
- [Learning to Generate 3D Shapes from a Single Example](https://mlsanity.com/paper/2208.02946/) (2022)
- [Pointersect: Neural Rendering with Cloud-Ray Intersection](https://mlsanity.com/paper/2304.12390/) (2023)
- [SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshes](https://mlsanity.com/paper/2409.20562/) (2024)
- [Point Cloud Diffusion Models for Automatic Implant Generation](https://mlsanity.com/paper/2303.08061/) (2023)
- [NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matching](https://mlsanity.com/paper/2301.05839/) (2023)
- [Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes](https://mlsanity.com/paper/2312.04043/) (2023)
- [Deep Hybrid Self-Prior for Full 3D Mesh Generation](https://mlsanity.com/paper/2108.08017/) (2021)
- [Deep Surface Reconstruction from Point Clouds with Visibility Information](https://mlsanity.com/paper/2202.01810/) (2022)
- [SCoDA: Domain Adaptive Shape Completion for Real Scans](https://mlsanity.com/paper/2304.10179/) (2023)
- [Deep Internal Learning: Deep Learning from a Single Input](https://mlsanity.com/paper/2312.07425/) (2023)
- [Image Restoration by Deep Projected GSURE](https://mlsanity.com/paper/2102.02485/) (2021)
- [Learning the Geodesic Embedding with Graph Neural Networks](https://mlsanity.com/paper/2309.05613/) (2023)
- [Scalable Surface Reconstruction with Delaunay-Graph Neural Networks](https://mlsanity.com/paper/2107.06130/) (2021)
- [OReX: Object Reconstruction from Planar Cross-sections Using Neural Fields](https://mlsanity.com/paper/2211.12886/) (2022)
- [Mesh Density Adaptation for Template-based Shape Reconstruction](https://mlsanity.com/paper/2307.16205/) (2023)
- [Registered and Segmented Deformable Object Reconstruction from a Single View Point Cloud](https://mlsanity.com/paper/2311.07357/) (2023)
- [TetWeave: Isosurface Extraction using On-The-Fly Delaunay Tetrahedral Grids for Gradient-Based Mesh Optimization](https://mlsanity.com/paper/2505.04590/) (2025)
- [Neural Annotation Refinement: Development of a New 3D Dataset for Adrenal Gland Analysis](https://mlsanity.com/paper/2206.15328/) (2022)
- [Fast Point Cloud to Mesh Reconstruction for Deformable Object Tracking](https://mlsanity.com/paper/2311.02749/) (2023)
- [Mesh Draping: Parametrization-Free Neural Mesh Transfer](https://mlsanity.com/paper/2110.05433/) (2021)
- [Neural Implicit Heart Coordinates: 3D cardiac shape reconstruction from sparse segmentations](https://mlsanity.com/paper/2512.19316/) (2025)
- [Z2P: Instant Visualization of Point Clouds](https://mlsanity.com/paper/2105.14548/) (2021)
- [Black-Box Test-Time Shape REFINEment for Single View 3D Reconstruction](https://mlsanity.com/paper/2108.09911/) (2021)
- [Sensor Data Validation and Driving Safety in Autonomous Driving Systems](https://mlsanity.com/paper/2203.16130/) (2022)

## Abstract (arXiv)

In this paper, we introduce Point2Mesh, a technique for reconstructing a surface mesh from an input point cloud. Instead of explicitly specifying a prior that encodes the expected shape properties, the prior is defined automatically using the input point cloud, which we refer to as a self-prior. The self-prior encapsulates reoccurring geometric repetitions from a single shape within the weights of a deep neural network. We optimize the network weights to deform an initial mesh to shrink-wrap a single input point cloud. This explicitly considers the entire reconstructed shape, since shared local kernels are calculated to fit the overall object. The convolutional kernels are optimized globally across the entire shape, which inherently encourages local-scale geometric self-similarity across the shape surface. We show that shrink-wrapping a point cloud with a self-prior converges to a desirable solution; compared to a prescribed smoothness prior, which often becomes trapped in undesirable local minima. While the performance of traditional reconstruction approaches degrades in non-ideal conditions that are often present in real world scanning, i.e., unoriented normals, noise and missing (low density) parts, Point2Mesh is robust to non-ideal conditions. We demonstrate the performance of Point2Mesh on a large variety of shapes with varying complexity.