paper-with-me

홈 › Papers

OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer

2026-01-20 · Pengze Zhang, Yanze Wu, Mengtian Li, Xu Bai, Songtao Zhao, Fulong Ye, Chong Mou, Xinghui Li, Zhuowei Chen, Qian He, Mingyuan Gao arxiv

Videos convey richer information than images or text, capturing both spatial and temporal dynamics. However, most existing video customization methods rely on reference images or task-specific temporal priors, failing to fully exploit the rich spatio-temporal information inherent in videos, thereby limiting flexibility and generalization in video generation. To address these limitations, we propose OmniTransfer, a unified framework for spatio-temporal video transfer. It leverages multi-view information across frames to enhance appearance consistency and exploits temporal cues to enable fine-grained temporal control. To unify various video transfer tasks, OmniTransfer incorporates three key designs: Task-aware Positional Bias that adaptively leverages reference video information to improve temporal alignment or appearance consistency; Reference-decoupled Causal Learning separating reference and target branches to enable precise reference transfer while improving efficiency; and Task-adaptive Multimodal Alignment using multimodal semantic guidance to dynamically distinguish and tackle different tasks. Extensive experiments show that OmniTransfer outperforms existing methods in appearance (ID and style) and temporal transfer (camera movement and video effects), while matching pose-guided methods in motion transfer without using pose, establishing a new paradigm for flexible, high-fidelity video generation.

📄 PDF Abstract BibTeX arXiv:2601.14250

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

Learning Transferable Spatiotemporal Representations from Natural Script Knowledge

2022-09-30 · CVPR 2023 1 · Ziyun Zeng, Yuying Ge, Xihui Liu, Bin Chen 외

Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years. Despite some progress, existing methods are mostly limited to highly curated dat…

DescriptiveRepresentation LearningVideo Understanding

Representing Videos Using Mid-level Discriminative Patches

2013-06-01 · CVPR 2013 6 · Arpit Jain, Abhinav Gupta, Mikel Rodriguez, Larry S. Davis

representation for videos based on mid-level discriminative spatio-temporal patches. These spatio-temporal patches might correspond to a primitive human action, a semantic object, or perhaps a random but informative spat…

Action ClassificationGeneral Classification

DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences

2026-06-26 · Yankai Yang, Yancheng Long, Bin Wen, Fan Yang 외 arxiv

Video multimodal large language models have made strong progress on open-ended video understanding, but they still lack precise local spatiotemporal perception. When two videos share almost the same global semantics and …

Orthogonal Spatial-temporal Distributional Transfer for 4D Generation

2026-03-05 · Wei Liu, Shengqiong Wu, Bobo Li, Haoyu Zhao 외 arxiv

In the AIGC era, generating high-quality 4D content has garnered increasing research attention. Unfortunately, current 4D synthesis research is severely constrained by the lack of large-scale 4D datasets, preventing mode…

STDD: Spatio-Temporal Dual Diffusion for Video Generation

2025-01-01 · CVPR 2025 1 · Shuaizhen Yao, Xiaoya Zhang, Xin Liu, Mengyi Liu 외

Diffusion probabilistic model is becoming the cornerstone of data generation, especially generating high-quality images. As an extension, video diffusion generation is in urgent need of a principled temporal-sequence…

Text-to-Video GenerationVideo Generation