# Dense 3D Object Reconstruction from a Single Depth View

arXiv: https://arxiv.org/abs/1802.00411 · HTML: https://mlsanity.com/paper/1802.00411/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Feb 2018.

## Built on by (most cited first, 24 of 24)

- [Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation](https://mlsanity.com/paper/2404.15506/) (2024)
- [3D Semantic Scene Completion: a Survey](https://mlsanity.com/paper/2103.07466/) (2021)
- [CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation](https://mlsanity.com/paper/2203.01929/) (2022)
- [DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images](https://mlsanity.com/paper/2208.07227/) (2022)
- [NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videos](https://mlsanity.com/paper/2312.06398/) (2023)
- [SP-GAN: Sphere-Guided 3D Shape Generation and Manipulation](https://mlsanity.com/paper/2108.04476/) (2021)
- [Generalizable Neural Radiance Fields for Novel View Synthesis with Transformer](https://mlsanity.com/paper/2206.05375/) (2022)
- [Learning Local Displacements for Point Cloud Completion](https://mlsanity.com/paper/2203.16600/) (2022)
- [RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds](https://mlsanity.com/paper/2204.09138/) (2022)
- [FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity](https://mlsanity.com/paper/2506.07865/) (2025)
- [Light-weight Deformable Registration using Adversarial Learning with Distilling Knowledge](https://mlsanity.com/paper/2110.01293/) (2021)
- [RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency](https://mlsanity.com/paper/2310.19629/) (2023)
- [Towards Robust Monocular Depth Estimation in Non-Lambertian Surfaces](https://mlsanity.com/paper/2408.06083/) (2024)
- [SoftPool++: An Encoder-Decoder Network for Point Cloud Completion](https://mlsanity.com/paper/2205.03899/) (2022)
- [SIMstack: A Generative Shape and Instance Model for Unordered Object Stacks](https://mlsanity.com/paper/2103.16442/) (2021)
- [3D GANs and Latent Space: A comprehensive survey](https://mlsanity.com/paper/2304.03932/) (2023)
- [Self-supervised Latent Space Optimization with Nebula Variational Coding](https://mlsanity.com/paper/2506.01414/) (2025)
- [RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians](https://mlsanity.com/paper/2508.09830/) (2025)
- [Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Image](https://mlsanity.com/paper/2511.11074/) (2025)
- [Multiple View Performers for Shape Completion](https://mlsanity.com/paper/2209.06291/) (2022)
- [Pruning-based Topology Refinement of 3D Mesh using a 2D Alpha Mask](https://mlsanity.com/paper/2210.09148/) (2022)
- [Canonical Pose Reconstruction from Single Depth Image for 3D Non-rigid Pose Recovery on Limited Datasets](https://mlsanity.com/paper/2505.17992/) (2025)
- [Multispectral-NeRF:a multispectral modeling approach based on neural radiance fields](https://mlsanity.com/paper/2509.11169/) (2025)
- [GuideCAD: A Lightweight Multimodal Framework for 3D CAD Model Generation via Prefix Embedding](https://mlsanity.com/paper/2606.07024/) (2026)

## Abstract (arXiv)

In this paper, we propose a novel approach, 3D-RecGAN++, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks. Unlike 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 with a high resolution of 256^3 by recovering 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 and real-world Kinect 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.