# GazeNeRF: 3D-Aware Gaze Redirection with Neural Radiance Fields

arXiv: https://arxiv.org/abs/2212.04823 · HTML: https://mlsanity.com/paper/2212.04823/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 53 references that are in the map.
- First posted on arXiv 8 Dec 2022.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis](https://mlsanity.com/paper/2110.08985/) (2021)
- [Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction](https://mlsanity.com/paper/2012.03065/) (2020)
- [Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation](https://mlsanity.com/paper/2104.11116/) (2021)
- [HeadNeRF: A Real-time NeRF-based Parametric Head Model](https://mlsanity.com/paper/2112.05637/) (2021)
- [CodeNeRF: Disentangled Neural Radiance Fields for Object Categories](https://mlsanity.com/paper/2109.01750/) (2021)
- [BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images](https://mlsanity.com/paper/2002.08988/) (2020)
- [Eye Tracking for Everyone](https://mlsanity.com/paper/1606.05814/) (2016)
- [Appearance-Based Gaze Estimation in the Wild](https://mlsanity.com/paper/1504.02863/) (2015)
- [ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation](https://mlsanity.com/paper/2007.15837/) (2020)
- [It's Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation](https://mlsanity.com/paper/1611.08860/) (2016)
- [MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation](https://mlsanity.com/paper/1711.09017/) (2017)
- [MoFaNeRF: Morphable Facial Neural Radiance Field](https://mlsanity.com/paper/2112.02308/) (2021)
- [Few-Shot Adaptive Gaze Estimation](https://mlsanity.com/paper/1905.01941/) (2019)
- [HoloGAN: Unsupervised learning of 3D representations from natural images](https://mlsanity.com/paper/1904.01326/) (2019)
- [Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulation](https://mlsanity.com/paper/2204.10850/) (2022)
- [FaceX-Zoo: A PyTorch Toolbox for Face Recognition](https://mlsanity.com/paper/2101.04407/) (2021)
- [Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis](https://mlsanity.com/paper/1904.10638/) (2019)
- [Unsupervised Representation Learning for Gaze Estimation](https://mlsanity.com/paper/1911.06939/) (2019)
- [Self-Learning Transformations for Improving Gaze and Head Redirection](https://mlsanity.com/paper/2010.12307/) (2020)

## Built on by (most cited first, 12 of 12)

- [Neural Radiance Field-based Visual Rendering: A Comprehensive Review](https://mlsanity.com/paper/2404.00714/) (2024)
- [Rotation-Constrained Cross-View Feature Fusion for Multi-View Appearance-based Gaze Estimation](https://mlsanity.com/paper/2305.12704/) (2023)
- [GazeGaussian: High-Fidelity Gaze Redirection with 3D Gaussian Splatting](https://mlsanity.com/paper/2411.12981/) (2024)
- [UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training](https://mlsanity.com/paper/2502.02307/) (2025)
- [High-Fidelity Eye Animatable Neural Radiance Fields for Human Face](https://mlsanity.com/paper/2308.00773/) (2023)
- [MomentsNeRF: Leveraging Orthogonal Moments for Few-Shot Neural Rendering](https://mlsanity.com/paper/2407.02668/) (2024)
- [Is It Certainly a Deepfake? Reliability Analysis in Detection & Generation Ecosystem](https://mlsanity.com/paper/2509.17550/) (2025)
- [Angle Range and Identity Similarity Enhanced Gaze and Head Redirection based on Synthetic data](https://mlsanity.com/paper/2309.05214/) (2023)
- [Methods and strategies for improving the novel view synthesis quality of neural radiation field](https://mlsanity.com/paper/2401.12451/) (2024)
- [GazePrior: Zero-Shot AR/VR Eye Tracking via Learned 3D Gaze Reconstruction](https://mlsanity.com/paper/2605.22359/) (2026)
- [Data-driven Head Motion Generation through Natural Gaze-Head Coordination](https://mlsanity.com/paper/2605.25810/) (2026)
- [GazeDiT: Gaze-Accurate Diffusion Image Generation for Eye Tracking via Spatial Conditioning](https://mlsanity.com/paper/2609.17814/) (2026)

## Abstract (arXiv)

We propose GazeNeRF, a 3D-aware method for the task of gaze redirection. Existing gaze redirection methods operate on 2D images and struggle to generate 3D consistent results. Instead, we build on the intuition that the face region and eyeballs are separate 3D structures that move in a coordinated yet independent fashion. Our method leverages recent advancements in conditional image-based neural radiance fields and proposes a two-stream architecture that predicts volumetric features for the face and eye regions separately. Rigidly transforming the eye features via a 3D rotation matrix provides fine-grained control over the desired gaze angle. The final, redirected image is then attained via differentiable volume compositing. Our experiments show that this architecture outperforms naively conditioned NeRF baselines as well as previous state-of-the-art 2D gaze redirection methods in terms of redirection accuracy and identity preservation.