# Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction

arXiv: https://arxiv.org/abs/2112.12484 · HTML: https://mlsanity.com/paper/2112.12484/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 41 references that are in the map.
- First posted on arXiv 23 Dec 2021.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://mlsanity.com/paper/1804.01654/) (2018)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (2019)
- [Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling](https://mlsanity.com/paper/1804.04610/) (2018)
- [Adaptive Prototype Learning and Allocation for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01893/) (2021)
- [Prototype Mixture Models for Few-shot Semantic Segmentation](https://mlsanity.com/paper/2008.03898/) (2020)
- [FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding](https://mlsanity.com/paper/2103.05950/) (2021)
- [Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images](https://mlsanity.com/paper/1901.11153/) (2019)
- [Charting the Right Manifold: Manifold Mixup for Few-shot Learning](https://mlsanity.com/paper/1907.12087/) (2019)
- [Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction](https://mlsanity.com/paper/1706.07036/) (2017)
- [PointMixup: Augmentation for Point Clouds](https://mlsanity.com/paper/2008.06374/) (2020)
- [Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation](https://mlsanity.com/paper/1908.01491/) (2019)
- [Meta-Learning with Warped Gradient Descent](https://mlsanity.com/paper/1909.00025/) (2019)
- [Generalized Few-Shot Object Detection without Forgetting](https://mlsanity.com/paper/2105.09491/) (2021)
- [Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images](https://mlsanity.com/paper/2006.12250/) (2020)
- [Learning Shape Priors for Single-View 3D Completion and Reconstruction](https://mlsanity.com/paper/1809.05068/) (2018)
- [Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve](https://mlsanity.com/paper/2007.13034/) (2020)
- [Associative Alignment for Few-shot Image Classification](https://mlsanity.com/paper/1912.05094/) (2019)
- [Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection](https://mlsanity.com/paper/2103.17115/) (2021)
- [CoReNet: Coherent 3D scene reconstruction from a single RGB image](https://mlsanity.com/paper/2004.12989/) (2020)
- [TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/1912.09033/) (2019)
- [Learning View Priors for Single-view 3D Reconstruction](https://mlsanity.com/paper/1811.10719/) (2018)
- [Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network](https://mlsanity.com/paper/1901.08906/) (2019)

## Built on by (most cited first, 5 of 5)

- [Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors](https://mlsanity.com/paper/2209.15383/) (2022)
- [Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network](https://mlsanity.com/paper/2208.00183/) (2022)
- [Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets](https://mlsanity.com/paper/2304.02847/) (2023)
- [Infinite Class Mixup](https://mlsanity.com/paper/2305.10293/) (2023)
- [3DMiner: Discovering Shapes from Large-Scale Unannotated Image Datasets](https://mlsanity.com/paper/2310.19188/) (2023)

## Abstract (arXiv)

We present a pose adaptive few-shot learning procedure and a two-stage data interpolation regularization, termed Pose Adaptive Dual Mixup (PADMix), for single-image 3D reconstruction. While augmentations via interpolating feature-label pairs are effective in classification tasks, they fall short in shape predictions potentially due to inconsistencies between interpolated products of two images and volumes when rendering viewpoints are unknown. PADMix targets this issue with two sets of mixup procedures performed sequentially. We first perform an input mixup which, combined with a pose adaptive learning procedure, is helpful in learning 2D feature extraction and pose adaptive latent encoding. The stagewise training allows us to build upon the pose invariant representations to perform a follow-up latent mixup under one-to-one correspondences between features and ground-truth volumes. PADMix significantly outperforms previous literature on few-shot settings over the ShapeNet dataset and sets new benchmarks on the more challenging real-world Pix3D dataset.