I2VControl: Disentangled and Unified Video Motion Synthesis Control

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Feng, Wanquan, Qi, Tianhao, Liu, Jiawei, Sun, Mingzhen, Tu, Pengqi, Ma, Tianxiang, Dai, Fei, Zhao, Songtao, Zhou, Siyu, He, Qian
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918107486879744
author Feng, Wanquan
Qi, Tianhao
Liu, Jiawei
Sun, Mingzhen
Tu, Pengqi
Ma, Tianxiang
Dai, Fei
Zhao, Songtao
Zhou, Siyu
He, Qian
author_facet Feng, Wanquan
Qi, Tianhao
Liu, Jiawei
Sun, Mingzhen
Tu, Pengqi
Ma, Tianxiang
Dai, Fei
Zhao, Songtao
Zhou, Siyu
He, Qian
contents Motion controllability is crucial in video synthesis. However, most previous methods are limited to single control types, and combining them often results in logical conflicts. In this paper, we propose a disentangled and unified framework, namely I2VControl, to overcome the logical conflicts. We rethink camera control, object dragging, and motion brush, reformulating all tasks into a consistent representation based on point trajectories, each managed by a dedicated formulation. Accordingly, we propose a spatial partitioning strategy, where each unit is assigned to a concomitant control category, enabling diverse control types to be dynamically orchestrated within a single synthesis pipeline without conflicts. Furthermore, we design an adapter structure that functions as a plug-in for pre-trained models and is agnostic to specific model architectures. We conduct extensive experiments, achieving excellent performance on various control tasks, and our method further facilitates user-driven creative combinations, enhancing innovation and creativity. Project page: https://wanquanf.github.io/I2VControl .
format Preprint
id arxiv_https___arxiv_org_abs_2411_17765
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle I2VControl: Disentangled and Unified Video Motion Synthesis Control
Feng, Wanquan
Qi, Tianhao
Liu, Jiawei
Sun, Mingzhen
Tu, Pengqi
Ma, Tianxiang
Dai, Fei
Zhao, Songtao
Zhou, Siyu
He, Qian
Computer Vision and Pattern Recognition
Motion controllability is crucial in video synthesis. However, most previous methods are limited to single control types, and combining them often results in logical conflicts. In this paper, we propose a disentangled and unified framework, namely I2VControl, to overcome the logical conflicts. We rethink camera control, object dragging, and motion brush, reformulating all tasks into a consistent representation based on point trajectories, each managed by a dedicated formulation. Accordingly, we propose a spatial partitioning strategy, where each unit is assigned to a concomitant control category, enabling diverse control types to be dynamically orchestrated within a single synthesis pipeline without conflicts. Furthermore, we design an adapter structure that functions as a plug-in for pre-trained models and is agnostic to specific model architectures. We conduct extensive experiments, achieving excellent performance on various control tasks, and our method further facilitates user-driven creative combinations, enhancing innovation and creativity. Project page: https://wanquanf.github.io/I2VControl .
title I2VControl: Disentangled and Unified Video Motion Synthesis Control
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.17765