Scholarlink

We leverage a family of Riemannian metrics to upsample low frame rate animations for creative design and compression applications in computer graphics. Our method interpolates animated characters’ bone orientations along various geodesics from a family of invariant Riemannian metrics on a product of SO(3) manifolds. For compression, an optimization step selects the best-fitting metric. We show that our approach outperforms existing techniques.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Learning Riemannian Metrics for Interpolating Animations

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Sarah Kushner,
  • Vismay Modi,
  • Nina Miolane

摘要

We leverage a family of Riemannian metrics to upsample low frame rate animations for creative design and compression applications in computer graphics. Our method interpolates animated characters’ bone orientations along various geodesics from a family of invariant Riemannian metrics on a product of SO(3) manifolds. For compression, an optimization step selects the best-fitting metric. We show that our approach outperforms existing techniques.