# GAGAN: Geometry-Aware Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1712.00684 · HTML: https://mlsanity.com/paper/1712.00684/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2017.

## Built on by (most cited first, 7 of 7)

- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [PVSeRF: Joint Pixel-, Voxel- and Surface-Aligned Radiance Field for Single-Image Novel View Synthesis](https://mlsanity.com/paper/2202.04879/) (2022)
- [SeCGAN: Parallel Conditional Generative Adversarial Networks for Face Editing via Semantic Consistency](https://mlsanity.com/paper/2111.09298/) (2021)
- [Skull-to-Face: Anatomy-Guided 3D Facial Reconstruction and Editing](https://mlsanity.com/paper/2403.16207/) (2024)
- [Group-disentangled Representation Learning with Weakly-Supervised Regularization](https://mlsanity.com/paper/2110.12185/) (2021)
- [F3A-GAN: Facial Flow for Face Animation with Generative Adversarial Networks](https://mlsanity.com/paper/2205.06204/) (2022)
- [Unsupervised Style-based Explicit 3D Face Reconstruction from Single Image](https://mlsanity.com/paper/2304.12455/) (2023)

## Abstract (arXiv)

Deep generative models learned through adversarial training have become increasingly popular for their ability to generate naturalistic image textures. However, aside from their texture, the visual appearance of objects is significantly influenced by their shape geometry; information which is not taken into account by existing generative models. This paper introduces the Geometry-Aware Generative Adversarial Networks (GAGAN) for incorporating geometric information into the image generation process. Specifically, in GAGAN the generator samples latent variables from the probability space of a statistical shape model. By mapping the output of the generator to a canonical coordinate frame through a differentiable geometric transformation, we enforce the geometry of the objects and add an implicit connection from the prior to the generated object. Experimental results on face generation indicate that the GAGAN can generate realistic images of faces with arbitrary facial attributes such as facial expression, pose, and morphology, that are of better quality than current GAN-based methods. Our method can be used to augment any existing GAN architecture and improve the quality of the images generated.