# Domain-Adaptive Single-View 3D Reconstruction

arXiv: https://arxiv.org/abs/1812.01742 · HTML: https://mlsanity.com/paper/1812.01742/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2018.

## Built on by (most cited first, 12 of 12)

- [Evaluation Gaps in Machine Learning Practice](https://mlsanity.com/paper/2205.05256/) (2022)
- [Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction](https://mlsanity.com/paper/2104.00858/) (2021)
- [Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors](https://mlsanity.com/paper/2209.15383/) (2022)
- [SGM3D: Stereo Guided Monocular 3D Object Detection](https://mlsanity.com/paper/2112.01914/) (2021)
- [SCoDA: Domain Adaptive Shape Completion for Real Scans](https://mlsanity.com/paper/2304.10179/) (2023)
- [GARNet: Global-Aware Multi-View 3D Reconstruction Network and the Cost-Performance Tradeoff](https://mlsanity.com/paper/2211.02299/) (2022)
- [Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimation](https://mlsanity.com/paper/2311.09500/) (2023)
- [Black-Box Test-Time Shape REFINEment for Single View 3D Reconstruction](https://mlsanity.com/paper/2108.09911/) (2021)
- [3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models](https://mlsanity.com/paper/2210.04265/) (2022)
- [Look, Cast and Mold: Learning 3D Shape Manifold from Single-view Synthetic Data](https://mlsanity.com/paper/2103.04789/) (2021)
- [GeT: Generative Target Structure Debiasing for Domain Adaptation](https://mlsanity.com/paper/2308.10205/) (2023)
- [Glissando-Net: Deep sinGLe vIew category level poSe eStimation ANd 3D recOnstruction](https://mlsanity.com/paper/2501.14896/) (2025)

## Abstract (arXiv)

Single-view 3D shape reconstruction is an important but challenging problem, mainly for two reasons. First, as shape annotation is very expensive to acquire, current methods rely on synthetic data, in which ground-truth 3D annotation is easy to obtain. However, this results in domain adaptation problem when applied to natural images. The second challenge is that there are multiple shapes that can explain a given 2D image. In this paper, we propose a framework to improve over these challenges using adversarial training. On one hand, we impose domain confusion between natural and synthetic image representations to reduce the distribution gap. On the other hand, we impose the reconstruction to be `realistic' by forcing it to lie on a (learned) manifold of realistic object shapes. Our experiments show that these constraints improve performance by a large margin over baseline reconstruction models. We achieve results competitive with the state of the art with a much simpler architecture.