# Look, Cast and Mold: Learning 3D Shape Manifold from Single-view Synthetic Data

arXiv: https://arxiv.org/abs/2103.04789 · HTML: https://mlsanity.com/paper/2103.04789/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 63 references that are in the map.
- First posted on arXiv 8 Mar 2021.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction](https://mlsanity.com/paper/1905.10711/) (2019)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling](https://mlsanity.com/paper/1804.04610/) (2018)
- [Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs](https://mlsanity.com/paper/1703.09438/) (2017)
- [Self-Correction for Human Parsing](https://mlsanity.com/paper/1910.09777/) (2019)
- [Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency](https://mlsanity.com/paper/1704.06254/) (2017)
- [Learning a Predictable and Generative Vector Representation for Objects](https://mlsanity.com/paper/1603.08637/) (2016)
- [Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images](https://mlsanity.com/paper/1901.11153/) (2019)
- [Cross-Domain Adaptation for Animal Pose Estimation](https://mlsanity.com/paper/1908.05806/) (2019)
- [Just Go with the Flow: Self-Supervised Scene Flow Estimation](https://mlsanity.com/paper/1912.00497/) (2019)
- [Hierarchical Surface Prediction for 3D Object Reconstruction](https://mlsanity.com/paper/1704.00710/) (2017)
- [Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/1904.00876/) (2019)
- [Learning Shape Priors for Single-View 3D Completion and Reconstruction](https://mlsanity.com/paper/1809.05068/) (2018)

## Built on by (most cited first, 1 of 1)

- [GARNet: Global-Aware Multi-View 3D Reconstruction Network and the Cost-Performance Tradeoff](https://mlsanity.com/paper/2211.02299/) (2022)

## Abstract (arXiv)

Inferring the stereo structure of objects in the real world is a challenging yet practical task. To equip deep models with this ability usually requires abundant 3D supervision which is hard to acquire. It is promising that we can simply benefit from synthetic data, where pairwise ground-truth is easy to access. Nevertheless, the domain gaps are nontrivial considering the variant texture, shape and context. To overcome these difficulties, we propose a Visio-Perceptual Adaptive Network for single-view 3D reconstruction, dubbed VPAN. To generalize the model towards a real scenario, we propose to fulfill several aspects: (1) Look: visually incorporate spatial structure from the single view to enhance the expressiveness of representation; (2) Cast: perceptually align the 2D image features to the 3D shape priors with cross-modal semantic contrastive mapping; (3) Mold: reconstruct stereo-shape of target by transforming embeddings into the desired manifold. Extensive experiments on several benchmarks demonstrate the effectiveness and robustness of the proposed method in learning the 3D shape manifold from synthetic data via a single-view. The proposed method outperforms state-of-the-arts on Pix3D dataset with IoU 0.292 and CD 0.108, and reaches IoU 0.329 and CD 0.104 on Pascal 3D+.