# Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors

arXiv: https://arxiv.org/abs/2004.06302 · HTML: https://mlsanity.com/paper/2004.06302/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2020.

## Built on by (most cited first, 10 of 10)

- [GenSDF: Two-Stage Learning of Generalizable Signed Distance Functions](https://mlsanity.com/paper/2206.02780/) (2022)
- [Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors](https://mlsanity.com/paper/2209.15383/) (2022)
- [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)
- [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)
- [A Kendall Shape Space Approach to 3D Shape Estimation from 2D Landmarks](https://mlsanity.com/paper/2207.12687/) (2022)
- [Learning Compositional Shape Priors for Few-Shot 3D Reconstruction](https://mlsanity.com/paper/2106.06440/) (2021)
- [A Fusion of Variational Distribution Priors and Saliency Map Replay for Continual 3D Reconstruction](https://mlsanity.com/paper/2308.08812/) (2023)

## Abstract (arXiv)

The impressive performance of deep convolutional neural networks in single-view 3D reconstruction suggests that these models perform non-trivial reasoning about the 3D structure of the output space. However, recent work has challenged this belief, showing that complex encoder-decoder architectures perform similarly to nearest-neighbor baselines or simple linear decoder models that exploit large amounts of per category data in standard benchmarks. On the other hand settings where 3D shape must be inferred for new categories with few examples are more natural and require models that generalize about shapes. In this work we demonstrate experimentally that naive baselines do not apply when the goal is to learn to reconstruct novel objects using very few examples, and that in a few-shot learning setting, the network must learn concepts that can be applied to new categories, avoiding rote memorization. To address deficiencies in existing approaches to this problem, we propose three approaches that efficiently integrate a class prior into a 3D reconstruction model, allowing to account for intra-class variability and imposing an implicit compositional structure that the model should learn. Experiments on the popular ShapeNet database demonstrate that our method significantly outperform existing baselines on this task in the few-shot setting.