# Self-supervised Learning of 3D Objects from Natural Images

arXiv: https://arxiv.org/abs/1911.08850 · HTML: https://mlsanity.com/paper/1911.08850/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2019.

## Built on by (most cited first, 3 of 3)

- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [GaussiGAN: Controllable Image Synthesis with 3D Gaussians from Unposed Silhouettes](https://mlsanity.com/paper/2106.13215/) (2021)
- [Multi-Category Mesh Reconstruction From Image Collections](https://mlsanity.com/paper/2110.11256/) (2021)

## Abstract (arXiv)

We present a method to learn single-view reconstruction of the 3D shape, pose, and texture of objects from categorized natural images in a self-supervised manner. Since this is a severely ill-posed problem, carefully designing a training method and introducing constraints are essential. To avoid the difficulty of training all elements at the same time, we propose training category-specific base shapes with fixed pose distribution and simple textures first, and subsequently training poses and textures using the obtained shapes. Another difficulty is that shapes and backgrounds sometimes become excessively complicated to mistakenly reconstruct textures on object surfaces. To suppress it, we propose using strong regularization and constraints on object surfaces and background images. With these two techniques, we demonstrate that we can use natural image collections such as CIFAR-10 and PASCAL objects for training, which indicates the possibility to realize 3D object reconstruction on diverse object categories beyond synthetic datasets.