# Training Data Generating Networks: Shape Reconstruction via Bi-level Optimization

arXiv: https://arxiv.org/abs/2010.08276 · HTML: https://mlsanity.com/paper/2010.08276/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2020.

## Built on by (most cited first, 4 of 4)

- [3DILG: Irregular Latent Grids for 3D Generative Modeling](https://mlsanity.com/paper/2205.13914/) (2022)
- [Neural Shape Deformation Priors](https://mlsanity.com/paper/2210.05616/) (2022)
- [Gradient-based Bi-level Optimization for Deep Learning: A Survey](https://mlsanity.com/paper/2207.11719/) (2022)
- [Shape2.5D: A Dataset of Texture-less Surfaces for Depth and Normals Estimation](https://mlsanity.com/paper/2406.15831/) (2024)

## Abstract (arXiv)

We propose a novel 3d shape representation for 3d shape reconstruction from a single image. Rather than predicting a shape directly, we train a network to generate a training set which will be fed into another learning algorithm to define the shape. The nested optimization problem can be modeled by bi-level optimization. Specifically, the algorithms for bi-level optimization are also being used in meta learning approaches for few-shot learning. Our framework establishes a link between 3D shape analysis and few-shot learning. We combine training data generating networks with bi-level optimization algorithms to obtain a complete framework for which all components can be jointly trained. We improve upon recent work on standard benchmarks for 3d shape reconstruction.