LiftAvatar：基于运动空间的表达控制3D高斯人偶动画
LiftAvatar: Kinematic-Space Completion for Expression-Controlled 3D Gaussian Avatar Animation
AI总结：
LiftAvatar通过多粒度表达控制和多参考条件机制，提升3D人偶动画的质量和可控性。
摘要：
我们提出了LiftAvatar，一种新的范式，用于在运动空间中完成稀疏单目观测（例如面部表情和头部姿态），并利用完成的信号驱动高质量的人偶动画。LiftAvatar是一种细粒度、表达可控的大型视频扩散Transformer，能够基于单张或多张参考图像合成高质量、时间一致的表达序列。关键思想是将不完整的输入数据提升到更丰富的运动表示中，从而在下游3D人偶管道中增强重建和动画效果。为此，我们引入了（i）一种多粒度表达控制方案，结合阴影图和表达系数以实现精确且稳定的驱动，以及（ii）一种多参考条件机制，聚合多个帧中的互补线索，从而实现强3D一致性和可控性。作为一种即插即用的增强器，LiftAvatar直接解决了由于日常单目视频中稀疏运动线索导致的3D高斯散点人偶的有限表达性和重建伪影问题。通过将不完整的观测扩展到多样的姿态-表情变化，LiftAvatar还能够从大规模视频生成模型中有效地将先验知识蒸馏到3D管道中，从而带来显著的提升。大量实验表明，LiftAvatar在动画质量和最先进3D人偶方法的定量指标上都表现出一致的提升，尤其是在极端、未见过的表情情况下。
英文摘要：
We present LiftAvatar, a new paradigm that completes sparse monocular observations in kinematic space (e.g., facial expressions and head pose) and uses the completed signals to drive high-fidelity avatar animation. LiftAvatar is a fine-grained, expression-controllable large-scale video diffusion Transformer that synthesizes high-quality, temporally coherent expression sequences conditioned on single or multiple reference images. The key idea is to lift incomplete input data into a richer kinematic representation, thereby strengthening both reconstruction and animation in downstream 3D avatar pipelines. To this end, we introduce (i) a multi-granularity expression control scheme that combines shading maps with expression coefficients for precise and stable driving, and (ii) a multi-reference conditioning mechanism that aggregates complementary cues from multiple frames, enabling strong 3D consistency and controllability. As a plug-and-play enhancer, LiftAvatar directly addresses the limited expressiveness and reconstruction artifacts of 3D Gaussian Splatting-based avatars caused by sparse kinematic cues in everyday monocular videos. By expanding incomplete observations into diverse pose-expression variations, LiftAvatar also enables effective prior distillation from large-scale video generative models into 3D pipelines, leading to substantial gains. Extensive experiments show that LiftAvatar consistently boosts animation quality and quantitative metrics of state-of-the-art 3D avatar methods, especially under extreme, unseen expressions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
