Video-Conditioned Generative Joint 2D-3D Hand Motion Recovery

  • 类型:arxiv
  • 标识:2610.10512
  • 链接:https://arxiv.org/abs/2610.10512
  • 主分类:multimodal
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar
  • S2被引:0
  • 影响力被引:0
  • TLDR:JoHan, a unified generative framework that recovers hand motion directly from video sequences without relying on intermediate per-frame pose predictions, and captures much better hand-motion dynamics, producing significantly smoother motion than previous methods while maintaining high per-frame pose accuracy.
  • 待LLM分类:否
  • 标题中文:视频条件下的生成式 2D-3D 联合手部运动恢复
  • TLDR中文:JoHan 是一个统一的生成式框架,直接从视频序列恢复手部运动,不依赖逐帧中间姿态预测,能更好地建模手部运动动态,在保持较高逐帧姿态精度的同时生成显著更平滑的运动。
  • 来源文件:
  • /inbox/tom/_candidates/2026-10-13-rag-retrieval-reranking-candidates.json
  • [S2 enrich]