# Scan2Mesh: From Unstructured Range Scans to 3D Meshes

arXiv: https://arxiv.org/abs/1811.10464 · HTML: https://mlsanity.com/paper/1811.10464/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2018.

## Built on by (most cited first, 30 of 51)

- [MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers](https://mlsanity.com/paper/2311.15475/) (2023)
- [Scaling Mesh Generation via Compressive Tokenization](https://mlsanity.com/paper/2411.07025/) (2024)
- [ROCA: Robust CAD Model Retrieval and Alignment from a Single Image](https://mlsanity.com/paper/2112.01988/) (2021)
- [ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model](https://mlsanity.com/paper/2207.09446/) (2022)
- [Subdivision-Based Mesh Convolution Networks](https://mlsanity.com/paper/2106.02285/) (2021)
- [HoloPart: Generative 3D Part Amodal Segmentation](https://mlsanity.com/paper/2504.07943/) (2025)
- [Neural Marching Cubes](https://mlsanity.com/paper/2106.11272/) (2021)
- [PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance](https://mlsanity.com/paper/2405.16890/) (2024)
- [GIFS: Neural Implicit Function for General Shape Representation](https://mlsanity.com/paper/2204.07126/) (2022)
- [Joint Learning of 3D Shape Retrieval and Deformation](https://mlsanity.com/paper/2101.07889/) (2021)
- [MeshArt: Generating Articulated Meshes with Structure-Guided Transformers](https://mlsanity.com/paper/2412.11596/) (2024)
- [Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image](https://mlsanity.com/paper/2108.09368/) (2021)
- [DiffComplete: Diffusion-based Generative 3D Shape Completion](https://mlsanity.com/paper/2306.16329/) (2023)
- [Neural Surface Maps](https://mlsanity.com/paper/2103.16942/) (2021)
- [An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion](https://mlsanity.com/paper/2408.03178/) (2024)
- [RetrievalFuse: Neural 3D Scene Reconstruction with a Database](https://mlsanity.com/paper/2104.00024/) (2021)
- [3PSDF: Three-Pole Signed Distance Function for Learning Surfaces with Arbitrary Topologies](https://mlsanity.com/paper/2205.15572/) (2022)
- [OctField: Hierarchical Implicit Functions for 3D Modeling](https://mlsanity.com/paper/2111.01067/) (2021)
- [PhysPart: Physically Plausible Part Completion for Interactable Objects](https://mlsanity.com/paper/2408.13724/) (2024)
- [Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.16761/) (2025)
- [PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories](https://mlsanity.com/paper/2206.04916/) (2022)
- [MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh](https://mlsanity.com/paper/2508.01242/) (2025)
- [Mending Neural Implicit Modeling for 3D Vehicle Reconstruction in the Wild](https://mlsanity.com/paper/2101.06860/) (2021)
- [NeuForm: Adaptive Overfitting for Neural Shape Editing](https://mlsanity.com/paper/2207.08890/) (2022)
- [Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation](https://mlsanity.com/paper/2501.14317/) (2025)
- [SPARF: Large-Scale Learning of 3D Sparse Radiance Fields from Few Input Images](https://mlsanity.com/paper/2212.09100/) (2022)
- [NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Dropping](https://mlsanity.com/paper/2111.15207/) (2021)
- [VertexRegen: Mesh Generation with Continuous Level of Detail](https://mlsanity.com/paper/2508.09062/) (2025)
- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesis](https://mlsanity.com/paper/2402.16994/) (2024)

## Abstract (arXiv)

We introduce Scan2Mesh, a novel data-driven generative approach which transforms an unstructured and potentially incomplete range scan into a structured 3D mesh representation. The main contribution of this work is a generative neural network architecture whose input is a range scan of a 3D object and whose output is an indexed face set conditioned on the input scan. In order to generate a 3D mesh as a set of vertices and face indices, the generative model builds on a series of proxy losses for vertices, edges, and faces. At each stage, we realize a one-to-one discrete mapping between the predicted and ground truth data points with a combination of convolutional- and graph neural network architectures. This enables our algorithm to predict a compact mesh representation similar to those created through manual artist effort using 3D modeling software. Our generated mesh results thus produce sharper, cleaner meshes with a fundamentally different structure from those generated through implicit functions, a first step in bridging the gap towards artist-created CAD models.