Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.11231 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915618476785664 |
|---|---|
| author | Panchalingam, Abiram Bodala, Indu Middleton, Stuart |
| author_facet | Panchalingam, Abiram Bodala, Indu Middleton, Stuart |
| contents | High-fidelity gaze redirection is critical for generating augmented data to improve the generalization of gaze estimators. 3D Gaussian Splatting (3DGS) models like GazeGaussian represent the state-of-the-art but can struggle with rendering subtle, continuous gaze shifts. In this paper, we propose DiT-Gaze, a framework that enhances 3D gaze redirection models using a novel combination of Diffusion Transformer (DiT), weak supervision across gaze angles, and an orthogonality constraint loss. DiT allows higher-fidelity image synthesis, while our weak supervision strategy using synthetically generated intermediate gaze angles provides a smooth manifold of gaze directions during training. The orthogonality constraint loss mathematically enforces the disentanglement of internal representations for gaze, head pose, and expression. Comprehensive experiments show that DiT-Gaze sets a new state-of-the-art in both perceptual quality and redirection accuracy, reducing the state-of-the-art gaze error by 4.1% to 6.353 degrees, providing a superior method for creating synthetic training data. Our code and models will be made available for the research community to benchmark against. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11231 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | 3D Gaussian and Diffusion-Based Gaze Redirection Panchalingam, Abiram Bodala, Indu Middleton, Stuart Computer Vision and Pattern Recognition Artificial Intelligence High-fidelity gaze redirection is critical for generating augmented data to improve the generalization of gaze estimators. 3D Gaussian Splatting (3DGS) models like GazeGaussian represent the state-of-the-art but can struggle with rendering subtle, continuous gaze shifts. In this paper, we propose DiT-Gaze, a framework that enhances 3D gaze redirection models using a novel combination of Diffusion Transformer (DiT), weak supervision across gaze angles, and an orthogonality constraint loss. DiT allows higher-fidelity image synthesis, while our weak supervision strategy using synthetically generated intermediate gaze angles provides a smooth manifold of gaze directions during training. The orthogonality constraint loss mathematically enforces the disentanglement of internal representations for gaze, head pose, and expression. Comprehensive experiments show that DiT-Gaze sets a new state-of-the-art in both perceptual quality and redirection accuracy, reducing the state-of-the-art gaze error by 4.1% to 6.353 degrees, providing a superior method for creating synthetic training data. Our code and models will be made available for the research community to benchmark against. |
| title | 3D Gaussian and Diffusion-Based Gaze Redirection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.11231 |