# 3D Reconstruction of Novel Object Shapes from Single Images

arXiv: https://arxiv.org/abs/2006.07752 · HTML: https://mlsanity.com/paper/2006.07752/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2020.

## Built on by (most cited first, 21 of 21)

- [Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models](https://mlsanity.com/paper/2406.08475/) (2024)
- [ZeroShape: Regression-based Zero-shot Shape Reconstruction](https://mlsanity.com/paper/2312.14198/) (2023)
- [CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization](https://mlsanity.com/paper/2402.17214/) (2024)
- [PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories](https://mlsanity.com/paper/2206.04916/) (2022)
- [ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency](https://mlsanity.com/paper/2304.06247/) (2023)
- [Gen-3Diffusion: Realistic Image-to-3D Generation via 2D & 3D Diffusion Synergy](https://mlsanity.com/paper/2412.06698/) (2024)
- [Single-view 3D Mesh Reconstruction for Seen and Unseen Categories](https://mlsanity.com/paper/2208.02676/) (2022)
- [Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors](https://mlsanity.com/paper/2104.00476/) (2021)
- [Planes vs. Chairs: Category-guided 3D shape learning without any 3D cues](https://mlsanity.com/paper/2204.10235/) (2022)
- [Graph-Guided Deformation for Point Cloud Completion](https://mlsanity.com/paper/2112.01840/) (2021)
- [Temporal Point Cloud Completion with Pose Disturbance](https://mlsanity.com/paper/2202.03084/) (2022)
- [Interactive Sketching of Mannequin Poses](https://mlsanity.com/paper/2212.07098/) (2022)
- [Learning Local Pattern Modularization for Point Cloud Reconstruction from Unseen Classes](https://mlsanity.com/paper/2408.14279/) (2024)
- [The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction](https://mlsanity.com/paper/2101.07295/) (2021)
- [Visual Enhanced 3D Point Cloud Reconstruction from A Single Image](https://mlsanity.com/paper/2108.07685/) (2021)
- [Taylor3DNet: Fast 3D Shape Inference With Landmark Points Based Taylor Series](https://mlsanity.com/paper/2201.06845/) (2022)
- [Recovering Detail in 3D Shapes Using Disparity Maps](https://mlsanity.com/paper/2207.00182/) (2022)
- [Are All Point Clouds Suitable for Completion? Weakly Supervised Quality Evaluation Network for Point Cloud Completion](https://mlsanity.com/paper/2303.01804/) (2023)
- [A Fusion of Variational Distribution Priors and Saliency Map Replay for Continual 3D Reconstruction](https://mlsanity.com/paper/2308.08812/) (2023)
- [Sketch2CAD: 3D CAD Model Reconstruction from 2D Sketch using Visual Transformer](https://mlsanity.com/paper/2309.16850/) (2023)
- [Point-MF: Stabilizing One-Step Mean Flows for Single-Image Point Cloud Reconstruction](https://mlsanity.com/paper/2604.24586/) (2026)

## Abstract (arXiv)

Accurately predicting the 3D shape of any arbitrary object in any pose from a single image is a key goal of computer vision research. This is challenging as it requires a model to learn a representation that can infer both the visible and occluded portions of any object using a limited training set. A training set that covers all possible object shapes is inherently infeasible. Such learning-based approaches are inherently vulnerable to overfitting, and successfully implementing them is a function of both the architecture design and the training approach. We present an extensive investigation of factors specific to architecture design, training, experiment design, and evaluation that influence reconstruction performance and measurement. We show that our proposed SDFNet achieves state-of-the-art performance on seen and unseen shapes relative to existing methods GenRe and OccNet. We provide the first large-scale evaluation of single image shape reconstruction to unseen objects. The source code, data and trained models can be found on https://github.com/rehg-lab/3DShapeGen.