用草图生成可控的多人3D动画，支持动作、接触和时间精细调节。
Sketch2Colab: Sketch-Conditioned Multi-Human Animation via Controllable Flow Distillation
- 通过草图条件扩散先验蒸馏出快速稳定的潜空间流模型
- 在CORE4D和InterHuman数据集上约束遵循度与感知质量更优，采样速度更快
- 引入连续时间马尔可夫链规划器，清晰建模多人交互状态切换
我们提出Sketch2Colab，将故事板风格的2D草图转化为具有物体意识的连贯3D多人运动，并实现对代理、关节、时序和接触的细粒度控制。基于扩散的运动生成器虽具高真实感，但通常依赖昂贵的多实体引导且强条件下的性能下降。Sketch2Colab则学习草图条件扩散先验，并将其蒸馏至潜空间的修正流学生模型中，实现快速稳定采样。为使运动严格遵循故事板，采用可微目标引导学生模型，强制执行关键帧、路径、接触与物理一致性。多人协作运动涉及离散的交互变化，如汇聚、接触形成、协同搬运或分离，单一连续流难以清晰序列化这些转换。为此，我们设计轻量级连续时间马尔可夫链（CTMC）规划器，追踪活跃交互模式并调节流以生成更清晰、同步的人-物-人运动。在CORE4D和InterHuman数据集上的实验表明，Sketch2Colab在约束遵循度与感知质量上优于基线，且采样速度显著快于纯扩散方法。
原文摘要 · Abstract (English)
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.
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。