Cepheid: スケールと構造を分離した異系統モーション補完
Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion
幾何系統をまたいでスパースな頂点変位から密なメッシュモーションを補完するため、残差の構造と物理スケールを分離して学習する手法を提案。骨格や対応付けなしで未知の布や脚式身体にも汎化する。
著者: Chih-Hai Su, Tsung-Wei Ke, Yu-Lun Liu
分類: cs.CV, cs.GR, cs.LG
原文アブストラクト
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: https://su-terry.github.io/cepheid-website/