# 3D Object Reconstruction from a Single Depth View with Adversarial Learning

arXiv: https://arxiv.org/abs/1708.07969 · HTML: https://mlsanity.com/paper/1708.07969/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2017.

## Built on by (most cited first, 26 of 26)

- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [BEHAVE: Dataset and Method for Tracking Human Object Interactions](https://mlsanity.com/paper/2204.06950/) (2022)
- [AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers](https://mlsanity.com/paper/2301.04545/) (2023)
- [Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images](https://mlsanity.com/paper/2503.13439/) (2025)
- [Learning Generative Models of Textured 3D Meshes from Real-World Images](https://mlsanity.com/paper/2103.15627/) (2021)
- [Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion](https://mlsanity.com/paper/2211.11674/) (2022)
- [DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness](https://mlsanity.com/paper/2503.22677/) (2025)
- [Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2308.12113/) (2023)
- [PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling](https://mlsanity.com/paper/2203.00914/) (2022)
- [3DRIMR: 3D Reconstruction and Imaging via mmWave Radar based on Deep Learning](https://mlsanity.com/paper/2108.02858/) (2021)
- [Learning Local Displacements for Point Cloud Completion](https://mlsanity.com/paper/2203.16600/) (2022)
- [Adversarial Score Distillation: When score distillation meets GAN](https://mlsanity.com/paper/2312.00739/) (2023)
- [FakeNews: GAN-based generation of realistic 3D volumetric data -- A systematic review and taxonomy](https://mlsanity.com/paper/2207.01390/) (2022)
- [KTNet: Knowledge Transfer for Unpaired 3D Shape Completion](https://mlsanity.com/paper/2111.11976/) (2021)
- [R2P: A Deep Learning Model from mmWave Radar to Point Cloud](https://mlsanity.com/paper/2207.10690/) (2022)
- [SoftPool++: An Encoder-Decoder Network for Point Cloud Completion](https://mlsanity.com/paper/2205.03899/) (2022)
- [DeepPoint: A Deep Learning Model for 3D Reconstruction in Point Clouds via mmWave Radar](https://mlsanity.com/paper/2109.09188/) (2021)
- [3D Plant Root Skeleton Detection and Extraction](https://mlsanity.com/paper/2508.08094/) (2025)
- [SIMstack: A Generative Shape and Instance Model for Unordered Object Stacks](https://mlsanity.com/paper/2103.16442/) (2021)
- [3D Reconstruction of Multiple Objects by mmWave Radar on UAV](https://mlsanity.com/paper/2211.02150/) (2022)
- [A Review on Oracle Issues in Machine Learning](https://mlsanity.com/paper/2105.01407/) (2021)
- [3D GANs and Latent Space: A comprehensive survey](https://mlsanity.com/paper/2304.03932/) (2023)
- [CompleteDT: Point Cloud Completion with Dense Augment Inference Transformers](https://mlsanity.com/paper/2205.14999/) (2022)
- [RefComp: A Reference-guided Unified Framework for Unpaired Point Cloud Completion](https://mlsanity.com/paper/2504.13788/) (2025)
- [PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restoration](https://mlsanity.com/paper/2605.25127/) (2026)
- [SBP-Net: Learning Thin Structure Reconstruction with Sliding-Box Projections](https://mlsanity.com/paper/2606.04251/) (2026)

## Abstract (arXiv)

In this paper, we propose a novel 3D-RecGAN approach, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks. Unlike the existing work which typically requires multiple views of the same object or class labels to recover the full 3D geometry, the proposed 3D-RecGAN only takes the voxel grid representation of a depth view of the object as input, and is able to generate the complete 3D occupancy grid by filling in the occluded/missing regions. The key idea is to combine the generative capabilities of autoencoders and the conditional Generative Adversarial Networks (GAN) framework, to infer accurate and fine-grained 3D structures of objects in high-dimensional voxel space. Extensive experiments on large synthetic datasets show that the proposed 3D-RecGAN significantly outperforms the state of the art in single view 3D object reconstruction, and is able to reconstruct unseen types of objects. Our code and data are available at: https://github.com/Yang7879/3D-RecGAN.