# Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction

arXiv: https://arxiv.org/abs/1912.10589 · HTML: https://mlsanity.com/paper/1912.10589/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2019.

## Built on by (most cited first, 17 of 17)

- [ShaRF: Shape-conditioned Radiance Fields from a Single View](https://mlsanity.com/paper/2102.08860/) (2021)
- [NeRD: Neural 3D Reflection Symmetry Detector](https://mlsanity.com/paper/2105.03211/) (2021)
- [Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction](https://mlsanity.com/paper/2104.00858/) (2021)
- [ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency](https://mlsanity.com/paper/2304.06247/) (2023)
- [3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework](https://mlsanity.com/paper/2512.17459/) (2025)
- [A Real World Dataset for Multi-view 3D Reconstruction](https://mlsanity.com/paper/2203.11397/) (2022)
- [Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation](https://mlsanity.com/paper/2411.17763/) (2024)
- [SIMstack: A Generative Shape and Instance Model for Unordered Object Stacks](https://mlsanity.com/paper/2103.16442/) (2021)
- [NeRD++: Improved 3D-mirror symmetry learning from a single image](https://mlsanity.com/paper/2112.12579/) (2021)
- [Shape Completion with Points in the Shadow](https://mlsanity.com/paper/2209.08345/) (2022)
- [GroundUp: Rapid Sketch-Based 3D City Massing](https://mlsanity.com/paper/2407.12739/) (2024)
- [Modeling 3D Surface Manifolds with a Locally Conditioned Atlas](https://mlsanity.com/paper/2102.05984/) (2021)
- [A Review of Deep Learning-Powered Mesh Reconstruction Methods](https://mlsanity.com/paper/2303.02879/) (2023)
- [Deep Sketch-Based 3D Modeling: A Survey](https://mlsanity.com/paper/2603.03287/) (2026)
- [Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Engine](https://mlsanity.com/paper/2111.10817/) (2021)
- [Glissando-Net: Deep sinGLe vIew category level poSe eStimation ANd 3D recOnstruction](https://mlsanity.com/paper/2501.14896/) (2025)
- [ArchSym: Detecting 3D-Grounded Architectural Symmetries in the Wild](https://mlsanity.com/paper/2604.22202/) (2026)

## Abstract (arXiv)

Reconstruction of a 3D shape from a single 2D image is a classical computer vision problem, whose difficulty stems from the inherent ambiguity of recovering occluded or only partially observed surfaces. Recent methods address this challenge through the use of largely unstructured neural networks that effectively distill conditional mapping and priors over 3D shape. In this work, we induce structure and geometric constraints by leveraging three core observations: (1) the surface of most everyday objects is often almost entirely exposed from pairs of typical opposite views; (2) everyday objects often exhibit global reflective symmetries which can be accurately predicted from single views; (3) opposite orthographic views of a 3D shape share consistent silhouettes. Following these observations, we first predict orthographic 2.5D visible surface maps (depth, normal and silhouette) from perspective 2D images, and detect global reflective symmetries in this data; second, we predict the back facing depth and normal maps using as input the front maps and, when available, the symmetric reflections of these maps; and finally, we reconstruct a 3D mesh from the union of these maps using a surface reconstruction method best suited for this data. Our experiments demonstrate that our framework outperforms state-of-the art approaches for 3D shape reconstructions from 2D and 2.5D data in terms of input fidelity and details preservation. Specifically, we achieve 12% better performance on average in ShapeNet benchmark dataset, and up to 19% for certain classes of objects (e.g., chairs and vessels).