Metraipolis › archive › dc_267cce450dcb

Rethinking Fixed Temporal Grids: Frequency-Disentangled Motion Generation — arXiv:2610.03012

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.03012
License (as archived)
CC0-1.0
Archived
2026-10-06T09:07:32.784Z
SHA-256 of the archived text
295c78b7c9b7f9ec61def53164dea96c6830a3ce7bbffa9540393e2ac96d1a79
Stable URL of this page
https://metraipolis.com/documento/dc_267cce450dcb

How to cite

Rethinking Fixed Temporal Grids: Frequency-Disentangled Motion Generation — arXiv:2610.03012 — arXiv (en), https://arxiv.org/abs/2610.03012 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_267cce450dcb (Metraipolis archive dc_267cce450dcb, sha256 295c78b7c9b7f9ec61def53164dea96c6830a3ce7bbffa9540393e2ac96d1a79)
BibTeX
@misc{dc267cce450dcb,
  title = {Rethinking Fixed Temporal Grids: Frequency-Disentangled Motion Generation — arXiv:2610.03012},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.03012},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_267cce450dcb; sha256 295c78b7c9b7f9ec61def53164dea96c6830a3ce7bbffa9540393e2ac96d1a79},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.03012. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Most human motion generation methods encode motion as tokens on a uniform temporal grid, where every token spans the same fixed time window. Human motion, however, is temporally heterogeneous: slowly evolving global trajectories coexist with rapid transient events such as foot contacts and joint impulses. Forcing such multi-scale dynamics onto tokens of identical temporal resolution entangles motion frequencies, leaving slow regions redundant while smoothing out the rapid details that distinguish realistic motion. We propose \textbf{FreqMo}, a scale-adaptive motion representation that decomposes motion into wavelet frequency bands, separating dynamics across temporal scales while preserving temporal localization and exact reconstruction. Unified Frequency Residual Quantization (UFRQ) then encodes all bands within a single shared codebook, compressing the token sequence threefold and enabling stable single-stage generation. Experiments show FreqMo attains SOTA fidelity with substantially improved high-frequency preservation, and the same decomposition transfers to continuous diffusion backbones.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-05 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.03012 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T08:21:44.192Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).