# Image2Mesh: A Learning Framework for Single Image 3D Reconstruction

arXiv: https://arxiv.org/abs/1711.10669 · HTML: https://mlsanity.com/paper/1711.10669/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2017.

## Built on by (most cited first, 29 of 29)

- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Stylizing 3D Scene via Implicit Representation and HyperNetwork](https://mlsanity.com/paper/2105.13016/) (2021)
- [CHORE: Contact, Human and Object REconstruction from a single RGB image](https://mlsanity.com/paper/2204.02445/) (2022)
- [Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketches](https://mlsanity.com/paper/2105.06663/) (2021)
- [CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing](https://mlsanity.com/paper/2108.11305/) (2021)
- [A Deep-Learning Approach For Direct Whole-Heart Mesh Reconstruction](https://mlsanity.com/paper/2102.07899/) (2021)
- [Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes](https://mlsanity.com/paper/2206.04942/) (2022)
- [Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving](https://mlsanity.com/paper/2412.06777/) (2024)
- [PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing](https://mlsanity.com/paper/2303.00137/) (2023)
- [StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects](https://mlsanity.com/paper/2105.08016/) (2021)
- [DeepMesh: Differentiable Iso-Surface Extraction](https://mlsanity.com/paper/2106.11795/) (2021)
- [Deep Hybrid Self-Prior for Full 3D Mesh Generation](https://mlsanity.com/paper/2108.08017/) (2021)
- [Single-view 3D Mesh Reconstruction for Seen and Unseen Categories](https://mlsanity.com/paper/2208.02676/) (2022)
- [Unsupervised Novel View Synthesis from a Single Image](https://mlsanity.com/paper/2102.03285/) (2021)
- [Shadows Shed Light on 3D Objects](https://mlsanity.com/paper/2206.08990/) (2022)
- [Geometric-Aware Low-Light Image and Video Enhancement via Depth Guidance](https://mlsanity.com/paper/2312.15855/) (2023)
- [Is Single-View Mesh Reconstruction Ready for Robotics?](https://mlsanity.com/paper/2505.17966/) (2025)
- [Deep3DSketch+: Rapid 3D Modeling from Single Free-hand Sketches](https://mlsanity.com/paper/2309.13006/) (2023)
- [Anytime 3D Object Reconstruction using Multi-modal Variational Autoencoder](https://mlsanity.com/paper/2101.10391/) (2021)
- [Anchor Distance for 3D Multi-Object Distance Estimation from 2D Single Shot](https://mlsanity.com/paper/2101.10399/) (2021)
- [Novel View Synthesis from a Single Image via Unsupervised learning](https://mlsanity.com/paper/2110.15569/) (2021)
- [CD2: Fine-grained 3D Mesh Reconstruction With Twice Chamfer Distance](https://mlsanity.com/paper/2206.00447/) (2022)
- [Visual Question Answering From Another Perspective: CLEVR Mental Rotation Tests](https://mlsanity.com/paper/2212.01639/) (2022)
- [Self-supervised learning of object pose estimation using keypoint prediction](https://mlsanity.com/paper/2302.07360/) (2023)
- [Intelligent Generation of Graphical Game Assets: A Conceptual Framework and Systematic Review of the State of the Art](https://mlsanity.com/paper/2311.10129/) (2023)
- [Learnable Triangulation for Deep Learning-based 3D Reconstruction of Objects of Arbitrary Topology from Single RGB Images](https://mlsanity.com/paper/2109.11844/) (2021)
- [3Deformer: A Common Framework for Image-Guided Mesh Deformation](https://mlsanity.com/paper/2307.09892/) (2023)
- [Neural Implicit Field Editing Considering Object-environment Interaction](https://mlsanity.com/paper/2311.00425/) (2023)
- [UNeR3D: Versatile and Scalable 3D RGB Point Cloud Generation from 2D Images in Unsupervised Reconstruction](https://mlsanity.com/paper/2312.06706/) (2023)

## Abstract (arXiv)

One challenge that remains open in 3D deep learning is how to efficiently represent 3D data to feed deep networks. Recent works have relied on volumetric or point cloud representations, but such approaches suffer from a number of issues such as computational complexity, unordered data, and lack of finer geometry. This paper demonstrates that a mesh representation (i.e. vertices and faces to form polygonal surfaces) is able to capture fine-grained geometry for 3D reconstruction tasks. A mesh however is also unstructured data similar to point clouds. We address this problem by proposing a learning framework to infer the parameters of a compact mesh representation rather than learning from the mesh itself. This compact representation encodes a mesh using free-form deformation and a sparse linear combination of models allowing us to reconstruct 3D meshes from single images. In contrast to prior work, we do not rely on silhouettes and landmarks to perform 3D reconstruction. We evaluate our method on synthetic and real-world datasets with very promising results. Our framework efficiently reconstructs 3D objects in a low-dimensional way while preserving its important geometrical aspects.