让用户通过深度控制3D轨迹，精准生成动态视频。
LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis
- 将物体掩码抽象为点，结合深度信息实现3D轨迹控制。
- 在真实图像生成视频时，能精确操控物体运动路径。
- 适合需要精细控制运动轨迹的视频生成应用。
拖拽式交互因其直观性被广泛用于图像到视频合成中的物体轨迹控制。然而，现有在2D空间中进行拖拽的方法在处理非平面运动时存在歧义。本文提出LeviTor，通过引入深度维度，允许用户为轨迹上每个点指定相对深度，从而在保持2D拖拽便捷性的同时，实现3D空间中的轨迹控制，拓展了创作可能性。我们提出一种开创性方法：将物体掩码抽象为少量聚类点，结合深度信息与实例信息，作为控制信号输入视频扩散模型。大量实验验证了LeviTor在从静态图像生成逼真视频时对物体运动的精确操控能力。代码已开源：https://github.com/ant-research/LeviTor。
原文摘要 · Abstract (English)
The intuitive nature of drag-based interaction has led to its growing adoption for controlling object trajectories in image-to-video synthesis. Still, existing methods that perform dragging in the 2D space usually face ambiguity when handling out-of-plane movements. In this work, we augment the interaction with a new dimension, i.e., the depth dimension, such that users are allowed to assign a relative depth for each point on the trajectory. That way, our new interaction paradigm not only inherits the convenience from 2D dragging, but facilitates trajectory control in the 3D space, broadening the scope of creativity. We propose a pioneering method for 3D trajectory control in image-to-video synthesis by abstracting object masks into a few cluster points. These points, accompanied by the depth information and the instance information, are finally fed into a video diffusion model as the control signal. Extensive experiments validate the effectiveness of our approach, dubbed LeviTor, in precisely manipulating the object movements when producing photo-realistic videos from static images. Our code is available at: https://github.com/ant-research/LeviTor.
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。