Sketch2Colab：基于可控流蒸馏的草图条件多人动画
Sketch2Colab: Sketch-Conditioned Multi-Human Animation via Controllable Flow Distillation
把草图条件扩散先验蒸馏成潜空间整流流学生模型，并用可微目标（关键帧、路径、接触、物理一致性）做引导，为视觉研究者提供了一条「强条件控制 + 快速采样」的运动生成范式；CTMC 规划器用于切换离散交互模式，可迁移到人-物-人交互或手-物操作序列建模。
原文依据 learns a sketch-conditioned diffusion prior and distills it into a rectified-flow student in latent space for fast, stable sampling
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 Sketch2Colab，它能把故事板风格的二维草图转换为连贯、具备物体感知的三维多人运动，并对智能体、关节、时序与接触实现细粒度控制。基于扩散的运动生成器真实感强，但往往依赖代价高昂的引导来实现多实体控制，且在强条件下性能退化。Sketch2Colab 转而学习一个草图条件扩散先验，并将其蒸馏为潜空间中的整流流学生模型，以实现快速、稳定的采样。为使运动紧密贴合故事板，我们用可微目标引导学生模型，强制满足关键帧、路径、接触与物理一致性。协作运动天然涉及交互的离散变化，例如汇聚、形成接触、协同搬运或分离，而仅靠连续流难以清晰地编排这些切换。为此我们引入一个轻量的连续时间马尔可夫链（CTMC）规划器，它跟踪当前活跃的交互模式并调制流，从而在人-物-人运动中产生更清晰、同步性更好的协调。在 CORE4D 与 InterHuman 上的实验表明，Sketch2Colab 在约束遵循度与感知质量上优于基线，同时采样速度显著快于纯扩散方案。
英文原文摘要 1293 字符
We present Sketch2Colab, which turns storyboard-style 2D sketches into coherent, object-aware 3D multi-human motion with fine-grained control over agents, joints, timing, and contacts. Diffusion-based motion generators offer strong realism but often rely on costly guidance for multi-entity control and degrade under strong conditioning. Sketch2Colab instead learns a sketch-conditioned diffusion prior and distills it into a rectified-flow student in latent space for fast, stable sampling. To make motion follow storyboards closely, we guide the student with differentiable objectives that enforce keyframes, paths, contacts, and physical consistency. Collaborative motion naturally involves discrete changes in interaction, such as converging, forming contact, cooperative transport, or disengaging, and a continuous flow alone struggles to sequence these shifts cleanly. We address this with a lightweight continuous-time Markov chain (CTMC) planner that tracks the active interaction regime and modulates the flow to produce clearer, synchronized coordination in human-object-human motion. Experiments on CORE4D and InterHuman show that Sketch2Colab outperforms baselines in constraint adherence and perceptual quality while sampling substantially faster than diffusion-only alternatives.