EUVIMEDEUVIMED entdecken
Crossref

Hierarchical Diffusion for Sparse-to-Full Human Motion Reconstruction

Fangyu Du, Yang Yang, Xuehao Gao, Hongye Hou, Chen Sun

IEEE Signal Processing Letters · 2026 · 33 · 2185-2189

DOI: 10.1109/lsp.2026.3694693 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Fangyu Du und 4 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Research and Development Program of Shaanxi Province of China, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human motion generation from sparse observations is an ill-posed problem in AR/VR, where head-mounted devices often capture only head and wrist trajectories. Prior methods usually reconstruct full-body motion in a single stage, forcing inference over a vast solution space and producing inaccurate lower-body motion, weak temporal coherence, and implausible sequences that degrade avatar embodiment. We present MAGE, a Multi-stage Avatar GEnerator based on hierarchical diffusion. Instead of predicting 22-joint motion at once, MAGE progressively refines motion from a coarse 6-part representation to full joints. Each stage injects stage-specific motion priors and uses intermediate predictions to constrain subsequent refinement, reducing ambiguity and stabilizing dynamics. Experiments on large-scale motion datasets show that MAGE improves reconstruction accuracy, temporal smoothness, and perceptual realism over state-of-the-art baselines, enabling more reliable full-body animation from minimal AR/VR sensing while preserving real-time interaction.

Förderung

  • National Natural Science Foundation of China
  • Key Research and Development Program of Shaanxi Province of China
  • National Key Research and Development Program of China

Zitieren

APA

Du, F., Yang, Y., Gao, X., Hou, H., & Sun, C. (2026). Hierarchical Diffusion for Sparse-to-Full Human Motion Reconstruction. IEEE Signal Processing Letters, 33, 2185-2189. https://doi.org/10.1109/lsp.2026.3694693

Vancouver

Du F, Yang Y, Gao X, Hou H, Sun C. Hierarchical Diffusion for Sparse-to-Full Human Motion Reconstruction. IEEE Signal Processing Letters. 2026;33:2185-2189. doi:10.1109/lsp.2026.3694693

BibTeX
@article{Du2026,
  author = {Du, Fangyu and Yang, Yang and Gao, Xuehao and Hou, Hongye and Sun, Chen},
  title = {Hierarchical Diffusion for Sparse-to-Full Human Motion Reconstruction},
  journal = {IEEE Signal Processing Letters},
  year = {2026},
  volume = {33},
  pages = {2185--2189},
  doi = {10.1109/lsp.2026.3694693}
}
Kostenlos starten →