# Few-Shot Generalization for Single-Image 3D Reconstruction via Priors

arXiv: https://arxiv.org/abs/1909.01205 · HTML: https://mlsanity.com/paper/1909.01205/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2019.

## Built on by (most cited first, 25 of 25)

- [PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction](https://mlsanity.com/paper/2302.10668/) (2023)
- [Multiview Compressive Coding for 3D Reconstruction](https://mlsanity.com/paper/2301.08247/) (2023)
- [Surface Reconstruction from Point Clouds by Learning Predictive Context Priors](https://mlsanity.com/paper/2204.11015/) (2022)
- [Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes](https://mlsanity.com/paper/2207.08656/) (2022)
- [DiffComplete: Diffusion-based Generative 3D Shape Completion](https://mlsanity.com/paper/2306.16329/) (2023)
- [GenSDF: Two-Stage Learning of Generalizable Signed Distance Functions](https://mlsanity.com/paper/2206.02780/) (2022)
- [PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories](https://mlsanity.com/paper/2206.04916/) (2022)
- [Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors](https://mlsanity.com/paper/2209.15383/) (2022)
- [CHORD: Category-level Hand-held Object Reconstruction via Shape Deformation](https://mlsanity.com/paper/2308.10574/) (2023)
- [Single-view 3D Mesh Reconstruction for Seen and Unseen Categories](https://mlsanity.com/paper/2208.02676/) (2022)
- [Planes vs. Chairs: Category-guided 3D shape learning without any 3D cues](https://mlsanity.com/paper/2204.10235/) (2022)
- [Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network](https://mlsanity.com/paper/2208.00183/) (2022)
- [Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Clouds](https://mlsanity.com/paper/2203.16001/) (2022)
- [3D Shape Completion on Unseen Categories:A Weakly-supervised Approach](https://mlsanity.com/paper/2401.10578/) (2024)
- [Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction](https://mlsanity.com/paper/2112.12484/) (2021)
- [Category-Agnostic 6D Pose Estimation with Conditional Neural Processes](https://mlsanity.com/paper/2206.07162/) (2022)
- [Black-Box Test-Time Shape REFINEment for Single View 3D Reconstruction](https://mlsanity.com/paper/2108.09911/) (2021)
- [Budget-aware Few-shot Learning via Graph Convolutional Network](https://mlsanity.com/paper/2201.02304/) (2022)
- [Learning Local Pattern Modularization for Point Cloud Reconstruction from Unseen Classes](https://mlsanity.com/paper/2408.14279/) (2024)
- [Learning Compositional Shape Priors for Few-Shot 3D Reconstruction](https://mlsanity.com/paper/2106.06440/) (2021)
- [IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Images](https://mlsanity.com/paper/2404.00269/) (2024)
- [BridgeShape: Latent Diffusion Schr"odinger Bridge for 3D Shape Completion](https://mlsanity.com/paper/2506.23205/) (2025)
- [A Fusion of Variational Distribution Priors and Saliency Map Replay for Continual 3D Reconstruction](https://mlsanity.com/paper/2308.08812/) (2023)
- [DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models](https://mlsanity.com/paper/2605.26949/) (2026)
- [Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation Learning](https://mlsanity.com/paper/2605.29661/) (2026)

## Abstract (arXiv)

Recent work on single-view 3D reconstruction shows impressive results, but has been restricted to a few fixed categories where extensive training data is available. The problem of generalizing these models to new classes with limited training data is largely open. To address this problem, we present a new model architecture that reframes single-view 3D reconstruction as learnt, category agnostic refinement of a provided, category-specific prior. The provided prior shape for a novel class can be obtained from as few as one 3D shape from this class. Our model can start reconstructing objects from the novel class using this prior without seeing any training image for this class and without any retraining. Our model outperforms category-agnostic baselines and remains competitive with more sophisticated baselines that finetune on the novel categories. Additionally, our network is capable of improving the reconstruction given multiple views despite not being trained on task of multi-view reconstruction.