Paper · arXiv 2408.11475
TrackGo: A Flexible and Efficient Method for Controllable Video Generation
Haitao Zhou, Chuang Wang, Rui Nie, Jinxiao Lin, Dongdong Yu, Qian Yu, Changhu Wang
TrackGo, using free-form masks and arrows along with TrackAdapter, achieves top performance in controlled video generation by enhancing pretrained temporal self-attention layers.
Abstract
Recent years have seen substantial progress in diffusion-based controllable video generation. However, achieving precise control in complex scenarios, including fine-grained object parts, sophisticated motion trajectories, and coherent background movement, remains a challenge. In this paper, we introduce TrackGo, a novel approach that leverages free-form masks and arrows for conditional video generation. This method offers users with a flexible and precise mechanism for manipulating video content. We also propose the TrackAdapter for control implementation, an efficient and lightweight adapter designed to be seamlessly integrated into the temporal self-attention layers of a pretrained video generation model. This design leverages our observation that the attention map of these layers can accurately activate regions corresponding to motion in videos. Our experimental results demonstrate that our new approach, enhanced by the TrackAdapter, achieves state-of-the-art performance on key metrics such as FVD, FID, and ObjMC scores. The project page of TrackGo can be found at: https://zhtjtcz.github.io/TrackGo-Page/