# DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation

arXiv: https://arxiv.org/abs/1607.07215 · HTML: https://mlsanity.com/paper/1607.07215/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2016.

## Built on by (most cited first, 27 of 27)

- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [GAN-Supervised Dense Visual Alignment](https://mlsanity.com/paper/2112.05143/) (2021)
- [Automatic Gaze Analysis: A Survey of Deep Learning based Approaches](https://mlsanity.com/paper/2108.05479/) (2021)
- [TRIPS: Trilinear Point Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2401.06003/) (2024)
- [EyeNeRF: A Hybrid Representation for Photorealistic Synthesis, Animation and Relighting of Human Eyes](https://mlsanity.com/paper/2206.08428/) (2022)
- [VET: Visual Error Tomography for Point Cloud Completion and High-Quality Neural Rendering](https://mlsanity.com/paper/2311.04634/) (2023)
- [GazeNeRF: 3D-Aware Gaze Redirection with Neural Radiance Fields](https://mlsanity.com/paper/2212.04823/) (2022)
- [Free-Viewpoint RGB-D Human Performance Capture and Rendering](https://mlsanity.com/paper/2112.13889/) (2021)
- [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)
- [Where Do Deep Fakes Look? Synthetic Face Detection via Gaze Tracking](https://mlsanity.com/paper/2101.01165/) (2021)
- [ADOP: Approximate Differentiable One-Pixel Point Rendering](https://mlsanity.com/paper/2110.06635/) (2021)
- [GazeGaussian: High-Fidelity Gaze Redirection with 3D Gaussian Splatting](https://mlsanity.com/paper/2411.12981/) (2024)
- [DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing](https://mlsanity.com/paper/2109.10737/) (2021)
- [ReDirTrans: Latent-to-Latent Translation for Gaze and Head Redirection](https://mlsanity.com/paper/2305.11452/) (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)
- [iWarpGAN: Disentangling Identity and Style to Generate Synthetic Iris Images](https://mlsanity.com/paper/2305.12596/) (2023)
- [Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps](https://mlsanity.com/paper/2206.02903/) (2022)
- [Differential Contrastive Training for Gaze Estimation](https://mlsanity.com/paper/2502.20128/) (2025)
- [Learning Gaze-aware Compositional GAN](https://mlsanity.com/paper/2405.20643/) (2024)
- ['Labelling the Gaps': A Weakly Supervised Automatic Eye Gaze Estimation](https://mlsanity.com/paper/2208.01840/) (2022)
- [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)
- [Neural Image Space Tessellation effect](https://mlsanity.com/paper/2602.23754/) (2026)
- [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)

In this work, we consider the task of generating highly-realistic images of a given face with a redirected gaze. We treat this problem as a specific instance of conditional image generation and suggest a new deep architecture that can handle this task very well as revealed by numerical comparison with prior art and a user study. Our deep architecture performs coarse-to-fine warping with an additional intensity correction of individual pixels. All these operations are performed in a feed-forward manner, and the parameters associated with different operations are learned jointly in the end-to-end fashion. After learning, the resulting neural network can synthesize images with manipulated gaze, while the redirection angle can be selected arbitrarily from a certain range and provided as an input to the network.