Metraipolis › archive › dc_e98710c42aec
ReFM: Semantic-Aware Refinement Flow Model for Motion Retargeting — arXiv:2609.32068
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32068
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:59:49.953Z
- SHA-256 of the archived text
39d94f894904d62684b3137f82e3cc632f391ea1365714cfe21ad99f4ab1805c- Stable URL of this page
https://metraipolis.com/documento/dc_e98710c42aec
How to cite
ReFM: Semantic-Aware Refinement Flow Model for Motion Retargeting — arXiv:2609.32068 — arXiv (en), https://arxiv.org/abs/2609.32068 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e98710c42aec (Metraipolis archive dc_e98710c42aec, sha256 39d94f894904d62684b3137f82e3cc632f391ea1365714cfe21ad99f4ab1805c)
BibTeX
@misc{dce98710c42aec,
title = {ReFM: Semantic-Aware Refinement Flow Model for Motion Retargeting — arXiv:2609.32068},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32068},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e98710c42aec; sha256 39d94f894904d62684b3137f82e3cc632f391ea1365714cfe21ad99f4ab1805c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32068. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Motion retargeting transfers motion across characters with different skeletal structures while preserving semantic intent and physical plausibility. Despite recent progress, two fundamental questions remain: (i) how can reliable source-motion semantics be learned without high-quality paired retargeting data, and (ii) how should retargeting be formulated when no reliable paired motion can serve as a definitive regression objective? Existing methods commonly preserve semantics by constraining predictions toward copied motions. However, such initializations entangle useful articulation cues with artifacts caused by mismatched skeletal proportions and body geometry. Moreover, directly regressing a final motion in one forward pass is restrictive because retargeting is inherently underdetermined, and the desired solution must balance semantic fidelity with target-specific physical and temporal constraints rather than match a unique paired target. Motivated by these limitations, we propose ReFM, a source-mesh-agnostic, energy-guided model that reformulates motion retargeting as progressive refinement. First, an SO(3) canonicalizer removes redundant global-orientation variations. Second, a cross-character semantic encoder, pretrained through contrastive learning, provides a character-invariant representation for both optimization guidance and semantic evaluation. ReFM then progressively refines an initialized target motion through a learned flow guided by semantic consistency, physical plausibility, temporal coherence, and minimal motion modification. The framework is compatible with different initialization strategies, including both direct motion copying and Autodesk HumanIK, an industry-standard full-body inverse-kinematics retargeting system. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Graphics (cs.GR). Pagina del lavoro: https://arxiv.org/abs/2609.32068 — 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 2026-10-07T20:29:02.219Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).