从单视角视频直接迁移3D角色动画，自动适配不同体型。
MorphGS: Morphology-Adaptive Articulated 3D Motion Transfer from Videos
- 用图像空间监督直接优化目标形态与姿态，不依赖中间重建。
- 在合成数据和真实视频上均优于基线方法，尤其对体型差异大者效果更佳。
- 适合需要快速迁移动画到不同角色的创作者或游戏开发者。
从单视角视频将关节式动作迁移到带绑定的3D角色极具挑战性，主要源于2D观测中的姿态模糊性以及源角色与目标角色之间的形态差异。现有方法通常采用先重建后重定向的范式，其迁移质量受限于中间3D重建结果，且仅适用于具有参数化模板的类别。我们提出MorphGS，将动作重定向建模为以目标为导向的分析-合成问题，通过图像空间监督直接优化目标形态与姿态。采用与骨骼耦合的形态参数化方法，将角色身份与随时间变化的关节旋转解耦；密集的2D-3D对应关系和合成视图提供互补的结构与多视角引导。在合成基准和真实视频上的实验表明，该方法持续优于基线。项目页面：https://xodus777.github.io/MorphGS/
原文摘要 · Abstract (English)
Transferring articulated motion from monocular videos to rigged 3D characters is challenging due to pose ambiguity in 2D observations and morphological differences between source and target. Existing approaches often follow a reconstruct-then-retarget paradigm, tying transfer quality to intermediate 3D reconstruction and limiting applicability to categories with parametric templates. We propose MorphGS, a framework that formulates motion retargeting as a target-driven analysis-by-synthesis problem, directly optimizing target morphology and pose through image-space supervision. A rig-coupled morphology parameterization factorizes character identity from time-varying joint rotations, while dense 2D-3D correspondences and synthesized views provide complementary structural and multi-view guidance. Experiments on synthetic benchmarks and real-world videos show consistent improvements over baselines. Project page: https://xodus777.github.io/MorphGS/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。