HuggingFace Daily Papers·· 1 天前
Cepheid：解耦尺度与结构，实现跨几何族的运动补全
Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion
AI 导读
Cepheid 通过将残差结构与物理尺度解耦，学习无量纲先验并从可观测数据估计幅度，从而突破跨几何族训练的缩放瓶颈。该统一模型在所有评测几何族上超越调和扩展，包括未见过的布料和腿式躯体，且无需骨架、配准或跨网格对应。同一先验无需重训练即可应用于点跟踪的动物视频和机器人抓取软体任务。
正文
Abstract:Sparse-to-dense motion completion recovers dense mesh motion from sparse vertex displacements. Residual priors trained on one geometry family frequently fail to beat parameter-free harmonic extension off-family. Moreover, cross-family training meets a scaling barrier: residual amplitude varies by more than an order of magnitude across geometry families and collapses as observations become denser. Since this scale depends on unknown target motion, it cannot be measured directly at test time. We decouple residual structure from physical scale by learning a dimensionless prior, estimating amplitude from observables and a lightweight correction fitted only on training sources. Our unified model surpasses harmonic extension across all evaluated families, including unseen cloth and legged bodies, without skeletons, registration, or cross-mesh correspondence. The same prior applies without retraining to point-tracked animal video and a robot grasping a soft body. Project page: this https URL
| Comments: | 31 pages. Project page: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.18871 [cs.CV] |
| (or arXiv:2610.18871v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18871 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chih-Hai Su [view email]
[v1]
Tue, 13 Oct 2026 17:59:53 UTC (15,237 KB)
来源：HuggingFace Daily Papers · arxiv.org