# Meshlet Priors for 3D Mesh Reconstruction

arXiv: https://arxiv.org/abs/2001.01744 · HTML: https://mlsanity.com/paper/2001.01744/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jan 2020.

## Built on by (most cited first, 23 of 23)

- [Shape As Points: A Differentiable Poisson Solver](https://mlsanity.com/paper/2106.03452/) (2021)
- [Neural Kernel Surface Reconstruction](https://mlsanity.com/paper/2305.19590/) (2023)
- [Neural Dual Contouring](https://mlsanity.com/paper/2202.01999/) (2022)
- [Neural Fields as Learnable Kernels for 3D Reconstruction](https://mlsanity.com/paper/2111.13674/) (2021)
- [Surface Reconstruction from Point Clouds: A Survey and a Benchmark](https://mlsanity.com/paper/2205.02413/) (2022)
- [Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matching](https://mlsanity.com/paper/2108.03746/) (2021)
- [SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminators](https://mlsanity.com/paper/2201.00112/) (2022)
- [Learning 3D Dense Correspondence via Canonical Point Autoencoder](https://mlsanity.com/paper/2107.04867/) (2021)
- [Moving in a 360 World: Synthesizing Panoramic Parallaxes from a Single Panorama](https://mlsanity.com/paper/2106.10859/) (2021)
- [Neural Vector Fields: Implicit Representation by Explicit Learning](https://mlsanity.com/paper/2303.04341/) (2023)
- [Deep Hybrid Self-Prior for Full 3D Mesh Generation](https://mlsanity.com/paper/2108.08017/) (2021)
- [Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors](https://mlsanity.com/paper/2104.00476/) (2021)
- [Enhancement of Novel View Synthesis Using Omnidirectional Image Completion](https://mlsanity.com/paper/2203.09957/) (2022)
- [What's the Situation with Intelligent Mesh Generation: A Survey and Perspectives](https://mlsanity.com/paper/2211.06009/) (2022)
- [SCoDA: Domain Adaptive Shape Completion for Real Scans](https://mlsanity.com/paper/2304.10179/) (2023)
- [Semi-signed prioritized neural fitting for surface reconstruction from unoriented point clouds](https://mlsanity.com/paper/2206.06715/) (2022)
- [Registered and Segmented Deformable Object Reconstruction from a Single View Point Cloud](https://mlsanity.com/paper/2311.07357/) (2023)
- [Minimal Neural Atlas: Parameterizing Complex Surfaces with Minimal Charts and Distortion](https://mlsanity.com/paper/2207.14782/) (2022)
- [Point2Quad: Generating Quad Meshes from Point Clouds via Face Prediction](https://mlsanity.com/paper/2504.19545/) (2025)
- [A Review of Deep Learning-Powered Mesh Reconstruction Methods](https://mlsanity.com/paper/2303.02879/) (2023)
- [Learning Joint Surface Atlases](https://mlsanity.com/paper/2206.06273/) (2022)
- [Neural Vector Fields: Generalizing Distance Vector Fields by Codebooks and Zero-Curl Regularization](https://mlsanity.com/paper/2309.01512/) (2023)
- [ShapeICP: Iterative Category-level Object Pose and Shape Estimation from Depth](https://mlsanity.com/paper/2408.13147/) (2024)

## Abstract (arXiv)

Estimating a mesh from an unordered set of sparse, noisy 3D points is a challenging problem that requires carefully selected priors. Existing hand-crafted priors, such as smoothness regularizers, impose an undesirable trade-off between attenuating noise and preserving local detail. Recent deep-learning approaches produce impressive results by learning priors directly from the data. However, the priors are learned at the object level, which makes these algorithms class-specific and even sensitive to the pose of the object. We introduce meshlets, small patches of mesh that we use to learn local shape priors. Meshlets act as a dictionary of local features and thus allow to use learned priors to reconstruct object meshes in any pose and from unseen classes, even when the noise is large and the samples sparse.