# A Survey on Deep Geometry Learning: From a Representation Perspective

arXiv: https://arxiv.org/abs/2002.07995 · HTML: https://mlsanity.com/paper/2002.07995/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2020.

## Built on by (most cited first, 19 of 19)

- [Subdivision-Based Mesh Convolution Networks](https://mlsanity.com/paper/2106.02285/) (2021)
- [Recursive-NeRF: An Efficient and Dynamically Growing NeRF](https://mlsanity.com/paper/2105.09103/) (2021)
- [OctField: Hierarchical Implicit Functions for 3D Modeling](https://mlsanity.com/paper/2111.01067/) (2021)
- [3D Vision with Transformers: A Survey](https://mlsanity.com/paper/2208.04309/) (2022)
- [HOSC: A Periodic Activation Function for Preserving Sharp Features in Implicit Neural Representations](https://mlsanity.com/paper/2401.10967/) (2024)
- [Laplacian2Mesh: Laplacian-Based Mesh Understanding](https://mlsanity.com/paper/2202.00307/) (2022)
- [What's the Situation with Intelligent Mesh Generation: A Survey and Perspectives](https://mlsanity.com/paper/2211.06009/) (2022)
- [Deep Deformation Detail Synthesis for Thin Shell Models](https://mlsanity.com/paper/2102.11541/) (2021)
- [Differentiable SAR Renderer and SAR Target Reconstruction](https://mlsanity.com/paper/2205.07099/) (2022)
- [3D Neural Operator-Based Flow Surrogates around 3D geometries: Signed Distance Functions and Derivative Constraints](https://mlsanity.com/paper/2503.17289/) (2025)
- [A Robust Scheme for 3D Point Cloud Copy Detection](https://mlsanity.com/paper/2110.00972/) (2021)
- [NASM: Neural Anisotropic Surface Meshing](https://mlsanity.com/paper/2410.23109/) (2024)
- [Cloud Sphere: A 3D Shape Representation via Progressive Deformation](https://mlsanity.com/paper/2112.11133/) (2021)
- [Long Range Pooling for 3D Large-Scale Scene Understanding](https://mlsanity.com/paper/2301.06962/) (2023)
- [A Task-driven Network for Mesh Classification and Semantic Part Segmentation](https://mlsanity.com/paper/2306.05246/) (2023)
- [Deep Spectral Meshes: Multi-Frequency Facial Mesh Processing with Graph Neural Networks](https://mlsanity.com/paper/2402.10365/) (2024)
- [3D Shape Generation: A Survey](https://mlsanity.com/paper/2506.22678/) (2025)
- [E2E-GNet: An End-to-End Skeleton-based Geometric Deep Neural Network for Human Motion Recognition](https://mlsanity.com/paper/2603.02477/) (2026)
- [PASR: Pose-Aware 3D Shape Retrieval from Occluded Single Views](https://mlsanity.com/paper/2604.22658/) (2026)

## Abstract (arXiv)

Researchers have now achieved great success on dealing with 2D images using deep learning. In recent years, 3D computer vision and Geometry Deep Learning gain more and more attention. Many advanced techniques for 3D shapes have been proposed for different applications. Unlike 2D images, which can be uniformly represented by regular grids of pixels, 3D shapes have various representations, such as depth and multi-view images, voxel-based representation, point-based representation, mesh-based representation, implicit surface representation, etc. However, the performance for different applications largely depends on the representation used, and there is no unique representation that works well for all applications. Therefore, in this survey, we review recent development in deep learning for 3D geometry from a representation perspective, summarizing the advantages and disadvantages of different representations in different applications. We also present existing datasets in these representations and further discuss future research directions.