# SurfNet: Generating 3D shape surfaces using deep residual networks

arXiv: https://arxiv.org/abs/1703.04079 · HTML: https://mlsanity.com/paper/1703.04079/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Mar 2017.

## Built on by (most cited first, 30 of 32)

- [Im2Vec: Synthesizing Vector Graphics without Vector Supervision](https://mlsanity.com/paper/2102.02798/) (2021)
- [3D Shape Generation with Grid-based Implicit Functions](https://mlsanity.com/paper/2107.10607/) (2021)
- [ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators](https://mlsanity.com/paper/2108.09432/) (2021)
- [HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D](https://mlsanity.com/paper/2312.15980/) (2023)
- [OctField: Hierarchical Implicit Functions for 3D Modeling](https://mlsanity.com/paper/2111.01067/) (2021)
- [GINA-3D: Learning to Generate Implicit Neural Assets in the Wild](https://mlsanity.com/paper/2304.02163/) (2023)
- [AI-Generated Content (AIGC) for Various Data Modalities: A Survey](https://mlsanity.com/paper/2308.14177/) (2023)
- [A Multi-Implicit Neural Representation for Fonts](https://mlsanity.com/paper/2106.06866/) (2021)
- [SP-GAN: Sphere-Guided 3D Shape Generation and Manipulation](https://mlsanity.com/paper/2108.04476/) (2021)
- [Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images](https://mlsanity.com/paper/2204.09866/) (2022)
- [Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis](https://mlsanity.com/paper/2212.08892/) (2022)
- [PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing](https://mlsanity.com/paper/2303.00137/) (2023)
- [Points2NeRF: Generating Neural Radiance Fields from 3D point cloud](https://mlsanity.com/paper/2206.01290/) (2022)
- [Deep Generative Model for Efficient 3D Airfoil Parameterization and Generation](https://mlsanity.com/paper/2101.02744/) (2021)
- [A Deep Signed Directional Distance Function for Object Shape Representation](https://mlsanity.com/paper/2107.11024/) (2021)
- [What's the Situation with Intelligent Mesh Generation: A Survey and Perspectives](https://mlsanity.com/paper/2211.06009/) (2022)
- [Airfoil GAN: Encoding and Synthesizing Airfoils for Aerodynamic Shape Optimization](https://mlsanity.com/paper/2101.04757/) (2021)
- [Dynamic 3D Point Cloud Sequences as 2D Videos](https://mlsanity.com/paper/2403.01129/) (2024)
- [Super-resolution 3D Human Shape from a Single Low-Resolution Image](https://mlsanity.com/paper/2208.10738/) (2022)
- [Deep Deformation Detail Synthesis for Thin Shell Models](https://mlsanity.com/paper/2102.11541/) (2021)
- [Learning Mesh Representations via Binary Space Partitioning Tree Networks](https://mlsanity.com/paper/2106.14274/) (2021)
- [HyperCube: Implicit Field Representations of Voxelized 3D Models](https://mlsanity.com/paper/2110.05770/) (2021)
- [A Review of Deep Learning-Powered Mesh Reconstruction Methods](https://mlsanity.com/paper/2303.02879/) (2023)
- [MARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learning](https://mlsanity.com/paper/2110.04830/) (2021)
- [TSCom-Net: Coarse-to-Fine 3D Textured Shape Completion Network](https://mlsanity.com/paper/2208.08768/) (2022)
- [An Embeddable Implicit IUVD Representation for Part-based 3D Human Surface Reconstruction](https://mlsanity.com/paper/2401.16810/) (2024)
- [Deep Generative Models on 3D Representations: A Survey](https://mlsanity.com/paper/2210.15663/) (2022)
- [Reconstruction Using the Invisible: Intuition from NIR and Metadata for Enhanced 3D Gaussian Splatting](https://mlsanity.com/paper/2508.14443/) (2025)
- [CurriFlow: Curriculum-Guided Depth Fusion with Optical Flow-Based Temporal Alignment for 3D Semantic Scene Completion](https://mlsanity.com/paper/2510.12362/) (2025)
- [Cloud Sphere: A 3D Shape Representation via Progressive Deformation](https://mlsanity.com/paper/2112.11133/) (2021)

## Abstract (arXiv)

3D shape models are naturally parameterized using vertices and faces, ie, composed of polygons forming a surface. However, current 3D learning paradigms for predictive and generative tasks using convolutional neural networks focus on a voxelized representation of the object. Lifting convolution operators from the traditional 2D to 3D results in high computational overhead with little additional benefit as most of the geometry information is contained on the surface boundary. Here we study the problem of directly generating the 3D shape surface of rigid and non-rigid shapes using deep convolutional neural networks. We develop a procedure to create consistent `geometry images' representing the shape surface of a category of 3D objects. We then use this consistent representation for category-specific shape surface generation from a parametric representation or an image by developing novel extensions of deep residual networks for the task of geometry image generation. Our experiments indicate that our network learns a meaningful representation of shape surfaces allowing it to interpolate between shape orientations and poses, invent new shape surfaces and reconstruct 3D shape surfaces from previously unseen images.