# Point2Quad: Generating Quad Meshes from Point Clouds via Face Prediction

arXiv: https://arxiv.org/abs/2504.19545 · HTML: https://mlsanity.com/paper/2504.19545/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 73 references that are in the map.
- First posted on arXiv 28 Apr 2025.

## Builds on (most cited first, 30 of 33)

- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://mlsanity.com/paper/1804.01654/) (2018)
- [Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis](https://mlsanity.com/paper/2111.04276/) (2021)
- [Shap-E: Generating Conditional 3D Implicit Functions](https://mlsanity.com/paper/2305.02463/) (2023)
- [Shape As Points: A Differentiable Poisson Solver](https://mlsanity.com/paper/2106.03452/) (2021)
- [Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces](https://mlsanity.com/paper/2011.13495/) (2020)
- [MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers](https://mlsanity.com/paper/2406.10163/) (2024)
- [CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner](https://mlsanity.com/paper/2405.14979/) (2024)
- [Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation](https://mlsanity.com/paper/1908.01491/) (2019)
- [Learning elementary structures for 3D shape generation and matching](https://mlsanity.com/paper/1908.04725/) (2019)
- [POCO: Point Convolution for Surface Reconstruction](https://mlsanity.com/paper/2201.01831/) (2022)
- [Neural Dual Contouring](https://mlsanity.com/paper/2202.01999/) (2022)
- [Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors](https://mlsanity.com/paper/2204.10603/) (2022)
- [Neural Fields as Learnable Kernels for 3D Reconstruction](https://mlsanity.com/paper/2111.13674/) (2021)
- [Scan2Mesh: From Unstructured Range Scans to 3D Meshes](https://mlsanity.com/paper/1811.10464/) (2018)
- [Neural Marching Cubes](https://mlsanity.com/paper/2106.11272/) (2021)
- [Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance](https://mlsanity.com/paper/2007.09267/) (2020)
- [Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations](https://mlsanity.com/paper/2012.06434/) (2020)
- [PointTriNet: Learned Triangulation of 3D Point Sets](https://mlsanity.com/paper/2005.02138/) (2020)
- [Meshlet Priors for 3D Mesh Reconstruction](https://mlsanity.com/paper/2001.01744/) (2020)
- [Learning Delaunay Surface Elements for Mesh Reconstruction](https://mlsanity.com/paper/2012.01203/) (2020)
- [Reinforcement learning for automatic quadrilateral mesh generation: a soft actor-critic approach](https://mlsanity.com/paper/2203.11203/) (2022)
- [NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Dropping](https://mlsanity.com/paper/2111.15207/) (2021)
- [Differentiable Surface Triangulation](https://mlsanity.com/paper/2109.10695/) (2021)
- [What's the Situation with Intelligent Mesh Generation: A Survey and Perspectives](https://mlsanity.com/paper/2211.06009/) (2022)
- [STAF: 3D Human Mesh Recovery from Video with Spatio-Temporal Alignment Fusion](https://mlsanity.com/paper/2401.01730/) (2024)
- [Multiview Textured Mesh Recovery by Differentiable Rendering](https://mlsanity.com/paper/2205.12468/) (2022)
- [SRL-Assisted AFM: Generating Planar Unstructured Quadrilateral Meshes with Supervised and Reinforcement Learning-Assisted Advancing Front Method](https://mlsanity.com/paper/2305.00540/) (2023)
- [Sketch2PQ: Freeform Planar Quadrilateral Mesh Design via a Single Sketch](https://mlsanity.com/paper/2201.09367/) (2022)
- [High-Quality Animatable Dynamic Garment Reconstruction from Monocular Videos](https://mlsanity.com/paper/2311.01214/) (2023)

## Built on by (most cited first, 5 of 5)

- [QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Models](https://mlsanity.com/paper/2509.21420/) (2025)
- [Mesh-Pro: Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh Generation](https://mlsanity.com/paper/2603.00526/) (2026)
- [QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning](https://mlsanity.com/paper/2605.16813/) (2026)
- [Look Both Ways Before You Cross: Lifting Cross Fields From 2D Visual Priors](https://mlsanity.com/paper/2605.26062/) (2026)
- [Q-MAGIC: Quad-only Mesh Autoregressive Generation via Singularity-Aware Circular Relative Offset Tokenization](https://mlsanity.com/paper/2610.19777/) (2026)

## Abstract (arXiv)

Quad meshes are essential in geometric modeling and computational mechanics. Although learning-based methods for triangle mesh demonstrate considerable advancements, quad mesh generation remains less explored due to the challenge of ensuring coplanarity, convexity, and quad-only meshes. In this paper, we present Point2Quad, the first learning-based method for quad-only mesh generation from point clouds. The key idea is learning to identify quad mesh with fused pointwise and facewise features. Specifically, Point2Quad begins with a k-NN-based candidate generation considering the coplanarity and squareness. Then, two encoders are followed to extract geometric and topological features that address the challenge of quad-related constraints, especially by combining in-depth quadrilaterals-specific characteristics. Subsequently, the extracted features are fused to train the classifier with a designed compound loss. The final results are derived after the refinement by a quad-specific post-processing. Extensive experiments on both clear and noise data demonstrate the effectiveness and superiority of Point2Quad, compared to baseline methods under comprehensive metrics.