MotionFlow:Learning Implicit Motion Flow for Complex Camera Trajectory Control in Video Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lei, Guojun, Wang, Chi, Wang, Yikai, Li, Hong, Song, Ying, Xu, Weiwei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908558509998080
author Lei, Guojun
Wang, Chi
Wang, Yikai
Li, Hong
Song, Ying
Xu, Weiwei
author_facet Lei, Guojun
Wang, Chi
Wang, Yikai
Li, Hong
Song, Ying
Xu, Weiwei
contents Generating videos guided by camera trajectories poses significant challenges in achieving consistency and generalizability, particularly when both camera and object motions are present. Existing approaches often attempt to learn these motions separately, which may lead to confusion regarding the relative motion between the camera and the objects. To address this challenge, we propose a novel approach that integrates both camera and object motions by converting them into the motion of corresponding pixels. Utilizing a stable diffusion network, we effectively learn reference motion maps in relation to the specified camera trajectory. These maps, along with an extracted semantic object prior, are then fed into an image-to-video network to generate the desired video that can accurately follow the designated camera trajectory while maintaining consistent object motions. Extensive experiments verify that our model outperforms SOTA methods by a large margin.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21119
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MotionFlow:Learning Implicit Motion Flow for Complex Camera Trajectory Control in Video Generation
Lei, Guojun
Wang, Chi
Wang, Yikai
Li, Hong
Song, Ying
Xu, Weiwei
Computer Vision and Pattern Recognition
Generating videos guided by camera trajectories poses significant challenges in achieving consistency and generalizability, particularly when both camera and object motions are present. Existing approaches often attempt to learn these motions separately, which may lead to confusion regarding the relative motion between the camera and the objects. To address this challenge, we propose a novel approach that integrates both camera and object motions by converting them into the motion of corresponding pixels. Utilizing a stable diffusion network, we effectively learn reference motion maps in relation to the specified camera trajectory. These maps, along with an extracted semantic object prior, are then fed into an image-to-video network to generate the desired video that can accurately follow the designated camera trajectory while maintaining consistent object motions. Extensive experiments verify that our model outperforms SOTA methods by a large margin.
title MotionFlow:Learning Implicit Motion Flow for Complex Camera Trajectory Control in Video Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.21119