首个面向毛孔级面部轨迹追踪的动态3D高斯泼溅基准数据集
PoreTrack3D: A Benchmark for Dynamic 3D Gaussian Splatting in Pore-Scale Facial Trajectory Tracking
- 构建包含44万条轨迹的动态3D高斯泼溅数据集，支持非刚性面部运动分析
- 涵盖超5.2万条超过10帧的长轨迹，68条完整覆盖150帧的人工审核轨迹
- 推动微小皮肤表面运动研究，适合高精度面部动作捕捉与重建领域
我们提出PoreTrack3D，首个用于孔隙尺度非刚性3D面部轨迹追踪的动态3D高斯泼溅基准。数据集共包含超过44万条面部轨迹，其中超过5.2万条长度超过10帧，包含68条人工审核、完整覆盖150帧的轨迹。据我们所知，PoreTrack3D是首个同时捕获传统面部关键点与毛孔级关键点轨迹的数据集，通过分析细微的皮肤表面运动，推动精细面部表情研究。我们在该数据集上系统评估了前沿动态3D高斯泼溅方法，建立了该领域的首个性能基准。整个数据集构建流程为高保真面部运动捕捉与动态3D重建提供了新框架。数据集公开获取：https://github.com/JHXion9/PoreTrack3D
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。