paper-with-me

홈 › Papers

Free-Form Motion Control: A Synthetic Video Generation Dataset with Controllable Camera and Object Motions

2025-01-02 · Xincheng Shuai, Henghui Ding, Zhenyuan Qin, Hao Luo, Xingjun Ma, DaCheng Tao

Controlling the movements of dynamic objects and the camera within generated videos is a meaningful yet challenging task. Due to the lack of datasets with comprehensive motion annotations, existing algorithms can not simultaneously control the motions of both camera and objects, resulting in limited controllability over generated contents. To address this issue and facilitate the research in this field, we introduce a Synthetic Dataset for Free-Form Motion Control (SynFMC). The proposed SynFMC dataset includes diverse objects and environments and covers various motion patterns according to specific rules, simulating common and complex real-world scenarios. The complete 6D pose information facilitates models learning to disentangle the motion effects from objects and the camera in a video. To validate the effectiveness and generalization of SynFMC, we further propose a method, Free-Form Motion Control (FMC). FMC enables independent or simultaneous control of object and camera movements, producing high-fidelity videos. Moreover, it is compatible with various personalized text-to-image (T2I) models for different content styles. Extensive experiments demonstrate that the proposed FMC outperforms previous methods across multiple scenarios.

📄 PDF Abstract BibTeX arXiv:2501.01425

Code (0)

등록된 구현이 없습니다.

Tasks

FormVideo Generation

Similar Papers 제목 키워드 기반

DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data

2026-04-02 · Wonjoon Jin, Jiyun Won, Janghyeok Han, Qi Dai 외 arxiv

Despite recent progress, video diffusion models still struggle to synthesize realistic videos involving highly dynamic motions or requiring fine-grained motion controllability. A central limitation lies in the scarcity o…

MotionMaster: Training-free Camera Motion Transfer For Video Generation

2024-04-24 · Teng Hu, Jiangning Zhang, Ran Yi, Yating Wang 외

The emergence of diffusion models has greatly propelled the progress in image and video generation. Recently, some efforts have been made in controllable video generation, including text-to-video generation and video mot…

DisentanglementMotion DisentanglementText-to-Video GenerationVideo Generation

SemanticMoments: Training-Free Motion Similarity via Third Moment Features

2026-02-09 · Saar Huberman, Kfir Goldberg, Or Patashnik, Sagie Benaim 외 arxiv

Retrieving videos based on semantic motion is a fundamental, yet unsolved, problem. Existing video representation approaches overly rely on static appearance and scene context rather than motion dynamics, a bias inherite…

QWERTY: Training-Free Motion Control via Query-Warped Video Diffusion Transformers

2026-07-02 · Kyobin Choo, Youngmin Kim, Hyunkyung Han, Geunrip Park 외 arxiv

Video diffusion transformers (DiTs) generate high-fidelity and temporally coherent videos, yet motion control remains implicit, primarily relying on text prompts. As a result, achieving desired motion often requires exte…

Prompt Engineering

VividCam: Learning Unconventional Camera Motions from Virtual Synthetic Videos

2025-10-28 · Qiucheng Wu, Handong Zhao, Zhixin Shu, Jing Shi 외 arxiv

Although recent text-to-video generative models are getting more capable of following external camera controls, imposed by either text descriptions or camera trajectories, they still struggle to generalize to unconventio…