Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2512.02648 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908708009672704 |
|---|---|
| author | Li, Dong Xiong, Jiahao Huang, Yingda Chang, Le |
| author_facet | Li, Dong Xiong, Jiahao Huang, Yingda Chang, Le |
| contents | We introduce PoreTrack3D, the first benchmark for dynamic 3D Gaussian splatting in pore-scale, non-rigid 3D facial trajectory tracking. It contains over 440,000 facial trajectories in total, among which more than 52,000 are longer than 10 frames, including 68 manually reviewed trajectories that span the entire 150 frames. To the best of our knowledge, PoreTrack3D is the first benchmark dataset to capture both traditional facial landmarks and pore-scale keypoints trajectory, advancing the study of fine-grained facial expressions through the analysis of subtle skin-surface motion. We systematically evaluate state-of-the-art dynamic 3D Gaussian splatting methods on PoreTrack3D, establishing the first performance baseline in this domain. Overall, the pipeline developed for this benchmark dataset's creation establishes a new framework for high-fidelity facial motion capture and dynamic 3D reconstruction. Our dataset are publicly available at: https://github.com/JHXion9/PoreTrack3D |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_02648 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PoreTrack3D: A Benchmark for Dynamic 3D Gaussian Splatting in Pore-Scale Facial Trajectory Tracking Li, Dong Xiong, Jiahao Huang, Yingda Chang, Le Computer Vision and Pattern Recognition We introduce PoreTrack3D, the first benchmark for dynamic 3D Gaussian splatting in pore-scale, non-rigid 3D facial trajectory tracking. It contains over 440,000 facial trajectories in total, among which more than 52,000 are longer than 10 frames, including 68 manually reviewed trajectories that span the entire 150 frames. To the best of our knowledge, PoreTrack3D is the first benchmark dataset to capture both traditional facial landmarks and pore-scale keypoints trajectory, advancing the study of fine-grained facial expressions through the analysis of subtle skin-surface motion. We systematically evaluate state-of-the-art dynamic 3D Gaussian splatting methods on PoreTrack3D, establishing the first performance baseline in this domain. Overall, the pipeline developed for this benchmark dataset's creation establishes a new framework for high-fidelity facial motion capture and dynamic 3D reconstruction. Our dataset are publicly available at: https://github.com/JHXion9/PoreTrack3D |
| title | PoreTrack3D: A Benchmark for Dynamic 3D Gaussian Splatting in Pore-Scale Facial Trajectory Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.02648 |