# Photo-Realistic Monocular Gaze Redirection Using Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1903.12530 · HTML: https://mlsanity.com/paper/1903.12530/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2019.

## Built on by (most cited first, 24 of 24)

- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark](https://mlsanity.com/paper/2104.12668/) (2021)
- [Automatic Gaze Analysis: A Survey of Deep Learning based Approaches](https://mlsanity.com/paper/2108.05479/) (2021)
- [EyeNeRF: A Hybrid Representation for Photorealistic Synthesis, Animation and Relighting of Human Eyes](https://mlsanity.com/paper/2206.08428/) (2022)
- [GazeNeRF: 3D-Aware Gaze Redirection with Neural Radiance Fields](https://mlsanity.com/paper/2212.04823/) (2022)
- [3DGazeNet: Generalizing Gaze Estimation with Weak-Supervision from Synthetic Views](https://mlsanity.com/paper/2212.02997/) (2022)
- [MTGLS: Multi-Task Gaze Estimation with Limited Supervision](https://mlsanity.com/paper/2110.12100/) (2021)
- [Free-HeadGAN: Neural Talking Head Synthesis with Explicit Gaze Control](https://mlsanity.com/paper/2208.02210/) (2022)
- [NeRF-Gaze: A Head-Eye Redirection Parametric Model for Gaze Estimation](https://mlsanity.com/paper/2212.14710/) (2022)
- [GazeGaussian: High-Fidelity Gaze Redirection with 3D Gaussian Splatting](https://mlsanity.com/paper/2411.12981/) (2024)
- [LatentGaze: Cross-Domain Gaze Estimation through Gaze-Aware Analytic Latent Code Manipulation](https://mlsanity.com/paper/2209.10171/) (2022)
- [ReDirTrans: Latent-to-Latent Translation for Gaze and Head Redirection](https://mlsanity.com/paper/2305.11452/) (2023)
- [High-Fidelity Eye Animatable Neural Radiance Fields for Human Face](https://mlsanity.com/paper/2308.00773/) (2023)
- [CUDA-GHR: Controllable Unsupervised Domain Adaptation for Gaze and Head Redirection](https://mlsanity.com/paper/2106.10852/) (2021)
- [Unsupervised High-Resolution Portrait Gaze Correction and Animation](https://mlsanity.com/paper/2207.00256/) (2022)
- [Domain-Adaptive Full-Face Gaze Estimation via Novel-View-Synthesis and Feature Disentanglement](https://mlsanity.com/paper/2305.16140/) (2023)
- [TextGaze: Gaze-Controllable Face Generation with Natural Language](https://mlsanity.com/paper/2404.17486/) (2024)
- [3D Prior is All You Need: Cross-Task Few-shot 2D Gaze Estimation](https://mlsanity.com/paper/2502.04074/) (2025)
- ['Labelling the Gaps': A Weakly Supervised Automatic Eye Gaze Estimation](https://mlsanity.com/paper/2208.01840/) (2022)
- [AI in HCI Design and User Experience](https://mlsanity.com/paper/2301.00987/) (2023)
- [EyeBAG: Accurate Control of Eye Blink and Gaze Based on Data Augmentation Leveraging Style Mixing](https://mlsanity.com/paper/2306.17391/) (2023)
- [Angle Range and Identity Similarity Enhanced Gaze and Head Redirection based on Synthetic data](https://mlsanity.com/paper/2309.05214/) (2023)
- [GazePrior: Zero-Shot AR/VR Eye Tracking via Learned 3D Gaze Reconstruction](https://mlsanity.com/paper/2605.22359/) (2026)
- [GazeDiT: Gaze-Accurate Diffusion Image Generation for Eye Tracking via Spatial Conditioning](https://mlsanity.com/paper/2609.17814/) (2026)

## Abstract (arXiv)

Gaze redirection is the task of changing the gaze to a desired direction for a given monocular eye patch image. Many applications such as videoconferencing, films, games, and generation of training data for gaze estimation require redirecting the gaze, without distorting the appearance of the area surrounding the eye and while producing photo-realistic images. Existing methods lack the ability to generate perceptually plausible images. In this work, we present a novel method to alleviate this problem by leveraging generative adversarial training to synthesize an eye image conditioned on a target gaze direction. Our method ensures perceptual similarity and consistency of synthesized images to the real images. Furthermore, a gaze estimation loss is used to control the gaze direction accurately. To attain high-quality images, we incorporate perceptual and cycle consistency losses into our architecture. In extensive evaluations we show that the proposed method outperforms state-of-the-art approaches in terms of both image quality and redirection precision. Finally, we show that generated images can bring significant improvement for the gaze estimation task if used to augment real training data.