FlexTraj：具备灵活点轨迹控制的图像到视频生成
FlexTraj: Image-to-Video Generation with Flexible Point Trajectory Control
用带时序一致轨迹 ID 与分割 ID 的点表示作为统一控制信号，并通过序列拼接而非 ControlNet 注入条件，为图像到视频生成提供对齐无关的稠密/稀疏轨迹控制，可直接复用于运动克隆、拖拽式生成与相机重定向等可控视频任务。
原文依据 FlexTraj employs an efficient sequence-concatenation scheme that achieves faster convergence, stronger controllability, and efficient inference
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 FlexTraj，一个具备灵活点轨迹控制的图像到视频生成框架。FlexTraj 引入统一的基于点的表示，为每个点编码时序一致的轨迹 ID、分割 ID 以及可选的颜色通道以提供外观线索，从而同时支持稠密与稀疏轨迹控制。FlexTraj 不通过词元拼接或 ControlNet 将轨迹条件注入视频生成器，而是采用高效的序列拼接方案，实现更快的收敛、更强的可控性与高效推理，同时在未对齐条件下保持鲁棒性。为训练这样一个统一的点轨迹控制视频生成器，FlexTraj 采用退火训练策略，逐步降低对完整监督与对齐条件的依赖。实验结果表明，FlexTraj 能够为视频生成实现多粒度、与对齐无关的轨迹控制，支持运动克隆、基于拖拽的图像到视频、运动插值、相机重定向、灵活动作控制以及网格动画等多种应用。
英文原文摘要 1155 字符
We present FlexTraj, a framework for image-to-video generation with flexible point trajectory control. FlexTraj introduces a unified point-based representation that encodes point with a temporally consistent trajectory ID, a segmentation ID, and an optional color channel for appearance cues, enabling both dense and sparse trajectory control. Instead of injecting trajectory conditions into the video generator through token concatenation or ControlNet, FlexTraj employs an efficient sequence-concatenation scheme that achieves faster convergence, stronger controllability, and efficient inference, while maintaining robustness under unaligned conditions. To train such a unified point trajectory-controlled video generator, FlexTraj adopts an annealing training strategy that gradually reduces reliance on complete supervision and aligned condition. Experimental results demonstrate that FlexTraj enables multi-granularity, alignment-agnostic trajectory control for video generation, supporting various applications such as motion cloning, drag-based image-to-video, motion interpolation, camera redirection, flexible action control and mesh animations.