无需训练即可精准控制动作空间位置，保持自然度。
ProjFlow: Projection Sampling with Flow Matching for Zero-Shot Exact Spatial Motion Control
- 基于骨骼拓扑设计新度量，协同修正全身动作。
- 在补全动作和2D转3D任务中精确满足约束条件。
- 适合需要快速、高精度空间控制的动画生成场景。
精确的空间控制生成人体动作是一项挑战性任务。现有方法通常需要特定任务训练或耗时优化，且硬性约束常破坏动作自然性。基于许多动画任务可表述为线性逆问题的观察，我们提出ProjFlow——一种无需训练的采样器，可在零样本条件下精确满足线性空间约束，同时保持动作真实性。其核心创新在于引入一种考虑骨骼结构的运动学感知度量，使约束修正能协同分布于整个骨架，避免简单投影带来的不自然伪影。此外，针对稀疏输入（如填补多个关键帧间的长空缺），我们提出使用随时间衰减的伪观测构建时变公式。在典型应用（动作补全、2D转3D）上的大量实验表明，ProjFlow实现了精确约束满足，在零样本基线上匹配或提升真实性，且性能媲美训练型控制器。
原文摘要 · Abstract (English)
Generating human motion with precise spatial control is a challenging problem. Existing approaches often require task-specific training or slow optimization, and enforcing hard constraints frequently disrupts motion naturalness. Building on the observation that many animation tasks can be formulated as a linear inverse problem, we introduce ProjFlow, a training-free sampler that achieves zero-shot, exact satisfaction of linear spatial constraints while preserving motion realism. Our key advance is a novel kinematics-aware metric that encodes skeletal topology. This metric allows the sampler to enforce hard constraints by distributing corrections coherently across the entire skeleton, avoiding the unnatural artifacts of naive projection. Furthermore, for sparse inputs, such as filling in long gaps between a few keyframes, we introduce a time-varying formulation using pseudo-observations that fade during sampling. Extensive experiments on representative applications, motion inpainting, and 2D-to-3D lifting, demonstrate that ProjFlow achieves exact constraint satisfaction and matches or improves realism over zero-shot baselines, while remaining competitive with training-based controllers.
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。