Saved in:
Bibliographic Details
Main Authors: Lei, Guojun, Zhang, Rong, Wang, Chi, Liu, Tianhang, Li, Hong, Ma, Zhiyuan, Xu, Weiwei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.21086
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912604795961344
author Lei, Guojun
Zhang, Rong
Wang, Chi
Liu, Tianhang
Li, Hong
Ma, Zhiyuan
Xu, Weiwei
author_facet Lei, Guojun
Zhang, Rong
Wang, Chi
Liu, Tianhang
Li, Hong
Ma, Zhiyuan
Xu, Weiwei
contents We propose a novel architecture UniTransfer, which introduces both spatial and diffusion timestep decomposition in a progressive paradigm, achieving precise and controllable video concept transfer. Specifically, in terms of spatial decomposition, we decouple videos into three key components: the foreground subject, the background, and the motion flow. Building upon this decomposed formulation, we further introduce a dual-to-single-stream DiT-based architecture for supporting fine-grained control over different components in the videos. We also introduce a self-supervised pretraining strategy based on random masking to enhance the decomposed representation learning from large-scale unlabeled video data. Inspired by the Chain-of-Thought reasoning paradigm, we further revisit the denoising diffusion process and propose a Chain-of-Prompt (CoP) mechanism to achieve the timestep decomposition. We decompose the denoising process into three stages of different granularity and leverage large language models (LLMs) for stage-specific instructions to guide the generation progressively. We also curate an animal-centric video dataset called OpenAnimal to facilitate the advancement and benchmarking of research in video concept transfer. Extensive experiments demonstrate that our method achieves high-quality and controllable video concept transfer across diverse reference images and scenes, surpassing existing baselines in both visual fidelity and editability. Web Page: https://yu-shaonian.github.io/UniTransfer-Web/
format Preprint
id arxiv_https___arxiv_org_abs_2509_21086
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UniTransfer: Video Concept Transfer via Progressive Spatial and Timestep Decomposition
Lei, Guojun
Zhang, Rong
Wang, Chi
Liu, Tianhang
Li, Hong
Ma, Zhiyuan
Xu, Weiwei
Computer Vision and Pattern Recognition
We propose a novel architecture UniTransfer, which introduces both spatial and diffusion timestep decomposition in a progressive paradigm, achieving precise and controllable video concept transfer. Specifically, in terms of spatial decomposition, we decouple videos into three key components: the foreground subject, the background, and the motion flow. Building upon this decomposed formulation, we further introduce a dual-to-single-stream DiT-based architecture for supporting fine-grained control over different components in the videos. We also introduce a self-supervised pretraining strategy based on random masking to enhance the decomposed representation learning from large-scale unlabeled video data. Inspired by the Chain-of-Thought reasoning paradigm, we further revisit the denoising diffusion process and propose a Chain-of-Prompt (CoP) mechanism to achieve the timestep decomposition. We decompose the denoising process into three stages of different granularity and leverage large language models (LLMs) for stage-specific instructions to guide the generation progressively. We also curate an animal-centric video dataset called OpenAnimal to facilitate the advancement and benchmarking of research in video concept transfer. Extensive experiments demonstrate that our method achieves high-quality and controllable video concept transfer across diverse reference images and scenes, surpassing existing baselines in both visual fidelity and editability. Web Page: https://yu-shaonian.github.io/UniTransfer-Web/
title UniTransfer: Video Concept Transfer via Progressive Spatial and Timestep Decomposition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.21086