# High Resolution Zero-Shot Domain Adaptation of Synthetically Rendered Face Images

arXiv: https://arxiv.org/abs/2006.15031 · HTML: https://mlsanity.com/paper/2006.15031/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2020.

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

- [Fake It Till You Make It: Face analysis in the wild using synthetic data alone](https://mlsanity.com/paper/2109.15102/) (2021)
- [Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data](https://mlsanity.com/paper/2311.18729/) (2023)
- [VariTex: Variational Neural Face Textures](https://mlsanity.com/paper/2104.05988/) (2021)
- [Enhancing the Authenticity of Rendered Portraits with Identity-Consistent Transfer Learning](https://mlsanity.com/paper/2310.04194/) (2023)

## Abstract (arXiv)

Generating photorealistic images of human faces at scale remains a prohibitively difficult task using computer graphics approaches. This is because these require the simulation of light to be photorealistic, which in turn requires physically accurate modelling of geometry, materials, and light sources, for both the head and the surrounding scene. Non-photorealistic renders however are increasingly easy to produce. In contrast to computer graphics approaches, generative models learned from more readily available 2D image data have been shown to produce samples of human faces that are hard to distinguish from real data. The process of learning usually corresponds to a loss of control over the shape and appearance of the generated images. For instance, even simple disentangling tasks such as modifying the hair independently of the face, which is trivial to accomplish in a computer graphics approach, remains an open research question. In this work, we propose an algorithm that matches a non-photorealistic, synthetically generated image to a latent vector of a pretrained StyleGAN2 model which, in turn, maps the vector to a photorealistic image of a person of the same pose, expression, hair, and lighting. In contrast to most previous work, we require no synthetic training data. To the best of our knowledge, this is the first algorithm of its kind to work at a resolution of 1K and represents a significant leap forward in visual realism.