RTGaze: Real-Time 3D-Aware Gaze Redirection from a Single Image
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917080235769856 |
|---|---|
| author | Wang, Hengfei Zhang, Zhongqun Cheng, Yihua Chang, Hyung Jin |
| author_facet | Wang, Hengfei Zhang, Zhongqun Cheng, Yihua Chang, Hyung Jin |
| contents | Gaze redirection methods aim to generate realistic human face images with controllable eye movement. However, recent methods often struggle with 3D consistency, efficiency, or quality, limiting their practical applications. In this work, we propose RTGaze, a real-time and high-quality gaze redirection method. Our approach learns a gaze-controllable facial representation from face images and gaze prompts, then decodes this representation via neural rendering for gaze redirection. Additionally, we distill face geometric priors from a pretrained 3D portrait generator to enhance generation quality. We evaluate RTGaze both qualitatively and quantitatively, demonstrating state-of-the-art performance in efficiency, redirection accuracy, and image quality across multiple datasets. Our system achieves real-time, 3D-aware gaze redirection with a feedforward network (~0.06 sec/image), making it 800x faster than the previous state-of-the-art 3D-aware methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11289 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RTGaze: Real-Time 3D-Aware Gaze Redirection from a Single Image Wang, Hengfei Zhang, Zhongqun Cheng, Yihua Chang, Hyung Jin Computer Vision and Pattern Recognition Gaze redirection methods aim to generate realistic human face images with controllable eye movement. However, recent methods often struggle with 3D consistency, efficiency, or quality, limiting their practical applications. In this work, we propose RTGaze, a real-time and high-quality gaze redirection method. Our approach learns a gaze-controllable facial representation from face images and gaze prompts, then decodes this representation via neural rendering for gaze redirection. Additionally, we distill face geometric priors from a pretrained 3D portrait generator to enhance generation quality. We evaluate RTGaze both qualitatively and quantitatively, demonstrating state-of-the-art performance in efficiency, redirection accuracy, and image quality across multiple datasets. Our system achieves real-time, 3D-aware gaze redirection with a feedforward network (~0.06 sec/image), making it 800x faster than the previous state-of-the-art 3D-aware methods. |
| title | RTGaze: Real-Time 3D-Aware Gaze Redirection from a Single Image |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.11289 |