# Synthesizing facial photometries and corresponding geometries using generative adversarial networks

arXiv: https://arxiv.org/abs/1901.06551 · HTML: https://mlsanity.com/paper/1901.06551/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jan 2019.

## Built on by (most cited first, 11 of 11)

- [Pixel Codec Avatars](https://mlsanity.com/paper/2104.04638/) (2021)
- [VariTex: Variational Neural Face Textures](https://mlsanity.com/paper/2104.05988/) (2021)
- [Implicit Neural Head Synthesis via Controllable Local Deformation Fields](https://mlsanity.com/paper/2304.11113/) (2023)
- [Exploring The Effect of High-frequency Components in GANs Training](https://mlsanity.com/paper/2103.11093/) (2021)
- [HQ3DAvatar: High Quality Controllable 3D Head Avatar](https://mlsanity.com/paper/2303.14471/) (2023)
- [Controllable 3D Generative Adversarial Face Model via Disentangling Shape and Appearance](https://mlsanity.com/paper/2208.14263/) (2022)
- [LUCAS: Layered Universal Codec Avatars](https://mlsanity.com/paper/2502.19739/) (2025)
- [Unsupervised High-Fidelity Facial Texture Generation and Reconstruction](https://mlsanity.com/paper/2110.04760/) (2021)
- [Structure-aware Editable Morphable Model for 3D Facial Detail Animation and Manipulation](https://mlsanity.com/paper/2207.09019/) (2022)
- [Intelligent Generation of Graphical Game Assets: A Conceptual Framework and Systematic Review of the State of the Art](https://mlsanity.com/paper/2311.10129/) (2023)
- [LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space](https://mlsanity.com/paper/2203.07881/) (2022)

## Abstract (arXiv)

Artificial data synthesis is currently a well studied topic with useful applications in data science, computer vision, graphics and many other fields. Generating realistic data is especially challenging since human perception is highly sensitive to non realistic appearance. In recent times, new levels of realism have been achieved by advances in GAN training procedures and architectures. These successful models, however, are tuned mostly for use with regularly sampled data such as images, audio and video. Despite the successful application of the architecture on these types of media, applying the same tools to geometric data poses a far greater challenge. The study of geometric deep learning is still a debated issue within the academic community as the lack of intrinsic parametrization inherent to geometric objects prohibits the direct use of convolutional filters, a main building block of today's machine learning systems. In this paper we propose a new method for generating realistic human facial geometries coupled with overlayed textures. We circumvent the parametrization issue by imposing a global mapping from our data to the unit rectangle. We further discuss how to design such a mapping to control the mapping distortion and conserve area within the mapped image. By representing geometric textures and geometries as images, we are able to use advanced GAN methodologies to generate new geometries. We address the often neglected topic of relation between texture and geometry and propose to use this correlation to match between generated textures and their corresponding geometries. We offer a new method for training GAN models on partially corrupted data. Finally, we provide empirical evidence demonstrating our generative model's ability to produce examples of new identities independent from the training data while maintaining a high level of realism, two traits that are often at odds.