ProjFlow：基于流匹配的投影采样实现零样本精确空间运动控制
ProjFlow: Projection Sampling with Flow Matching for Zero-Shot Exact Spatial Motion Control
把线性空间约束下的采样建模为线性逆问题，并用编码骨架拓扑的运动学感知度量做投影，这一免训练采样器思路可迁移到视觉中的轨迹/关键点/姿态等结构化输出的可控生成与补全。
原文依据 we introduce ProjFlow, a training-free sampler that achieves zero-shot, exact satisfaction of linear spatial constraints while preserving motion realism
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论生成具有精确空间控制的人体运动是一个具有挑战性的问题。现有方法通常需要任务特定的训练或缓慢的优化，而施加硬约束往往会破坏运动的自然性。基于许多动画任务可以被表述为线性逆问题这一观察，我们提出 ProjFlow，一种免训练的采样器，能够在保持运动真实感的同时，零样本、精确地满足线性空间约束。我们的关键进展是一种编码骨架拓扑的运动学感知度量。该度量使采样器能够通过在整个骨架上连贯地分配修正量来施加硬约束，从而避免朴素投影带来的不自然伪影。此外，对于稀疏输入，例如在少量关键帧之间填补长间隔，我们引入了一种使用在采样过程中逐渐衰减的伪观测的时变表述。在代表性应用——运动补全和 2D 到 3D 提升——上的大量实验表明，ProjFlow 实现了精确的约束满足，并在真实感上达到或超过零样本基线，同时与基于训练的控制器相比仍具竞争力。
英文原文摘要 1204 字符
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.