# Unsupervised Generative 3D Shape Learning from Natural Images

arXiv: https://arxiv.org/abs/1910.00287 · HTML: https://mlsanity.com/paper/1910.00287/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2019.

## Built on by (most cited first, 30 of 57)

- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion](https://mlsanity.com/paper/2212.06135/) (2022)
- [EMOCA: Emotion Driven Monocular Face Capture and Animation](https://mlsanity.com/paper/2204.11312/) (2022)
- [GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation](https://mlsanity.com/paper/2112.08867/) (2021)
- [Generative Neural Articulated Radiance Fields](https://mlsanity.com/paper/2206.14314/) (2022)
- [PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360circ](https://mlsanity.com/paper/2303.13071/) (2023)
- [SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis](https://mlsanity.com/paper/2404.04104/) (2024)
- [GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds](https://mlsanity.com/paper/2206.07255/) (2022)
- [A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis](https://mlsanity.com/paper/2110.15678/) (2021)
- [Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations](https://mlsanity.com/paper/2204.08839/) (2022)
- [AvatarGen: A 3D Generative Model for Animatable Human Avatars](https://mlsanity.com/paper/2211.14589/) (2022)
- [AG3D: Learning to Generate 3D Avatars from 2D Image Collections](https://mlsanity.com/paper/2305.02312/) (2023)
- [3D GAN Inversion for Controllable Portrait Image Animation](https://mlsanity.com/paper/2203.13441/) (2022)
- [AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars](https://mlsanity.com/paper/2210.06465/) (2022)
- [Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images](https://mlsanity.com/paper/2203.15926/) (2022)
- [VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relighting](https://mlsanity.com/paper/2201.04873/) (2022)
- [Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields](https://mlsanity.com/paper/2206.08361/) (2022)
- [RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models](https://mlsanity.com/paper/2407.06938/) (2024)
- [OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis](https://mlsanity.com/paper/2303.15539/) (2023)
- [HumanGen: Generating Human Radiance Fields with Explicit Priors](https://mlsanity.com/paper/2212.05321/) (2022)
- [DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model](https://mlsanity.com/paper/2211.16374/) (2022)
- [SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representation](https://mlsanity.com/paper/2404.05680/) (2024)
- [3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation](https://mlsanity.com/paper/2209.05434/) (2022)
- [GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild](https://mlsanity.com/paper/2211.12352/) (2022)
- [Learning monocular 3D reconstruction of articulated categories from motion](https://mlsanity.com/paper/2103.16352/) (2021)
- [Mimic3D: Thriving 3D-Aware GANs via 3D-to-2D Imitation](https://mlsanity.com/paper/2303.09036/) (2023)
- [3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping](https://mlsanity.com/paper/2212.07378/) (2022)
- [Compositional Generative Model of Unbounded 4D Cities](https://mlsanity.com/paper/2501.08983/) (2025)
- [En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data](https://mlsanity.com/paper/2401.01173/) (2024)
- [Efficient 3D Articulated Human Generation with Layered Surface Volumes](https://mlsanity.com/paper/2307.05462/) (2023)

## Abstract (arXiv)

In this paper we present, to the best of our knowledge, the first method to learn a generative model of 3D shapes from natural images in a fully unsupervised way. For example, we do not use any ground truth 3D or 2D annotations, stereo video, and ego-motion during the training. Our approach follows the general strategy of Generative Adversarial Networks, where an image generator network learns to create image samples that are realistic enough to fool a discriminator network into believing that they are natural images. In contrast, in our approach the image generation is split into 2 stages. In the first stage a generator network outputs 3D objects. In the second, a differentiable renderer produces an image of the 3D objects from random viewpoints. The key observation is that a realistic 3D object should yield a realistic rendering from any plausible viewpoint. Thus, by randomizing the choice of the viewpoint our proposed training forces the generator network to learn an interpretable 3D representation disentangled from the viewpoint. In this work, a 3D representation consists of a triangle mesh and a texture map that is used to color the triangle surface by using the UV-mapping technique. We provide analysis of our learning approach, expose its ambiguities and show how to overcome them. Experimentally, we demonstrate that our method can learn realistic 3D shapes of faces by using only the natural images of the FFHQ dataset.