Paper Detail

Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion

Chih-Hai Su, Tsung-Wei Ke, Yu-Lun Liu

arxiv Score 3.8

Published 2026-10-13 · First seen 2026-10-14

General AI

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: https://su-terry.github.io/cepheid-website/

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{su2026cepheid,
  title = {Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion},
  author = {Chih-Hai Su and Tsung-Wei Ke and Yu-Lun Liu},
  year = {2026},
  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 d},
  url = {https://arxiv.org/abs/2610.18871},
  keywords = {cs.CV, cs.GR, cs.LG},
  eprint = {2610.18871},
  archiveprefix = {arXiv},
}

Metadata

{}