Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jiao, Guanlong, Zhang, Chenyangguang, Xian, Jia Jun Cheng, Zhang, Zewei, Liao, Renjie
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.21466
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917517253935104
author Jiao, Guanlong
Zhang, Chenyangguang
Xian, Jia Jun Cheng
Zhang, Zewei
Liao, Renjie
author_facet Jiao, Guanlong
Zhang, Chenyangguang
Xian, Jia Jun Cheng
Zhang, Zewei
Liao, Renjie
contents Although existing video editing methods are generally feasible, they often require many costly iterations and still struggle to deliver high-quality yet satisfying editing results. We attribute this limitation to the prevalent data-to-data paradigm, which is less compatible with modern generative models than noise-to-data generation. To address this gap, we revisit video editing from a noise-to-data perspective and propose Streaming-Generation-based Video Editing (StreamGVE), which preserves few-step sampling while seamlessly injecting source-video conditions. Built on pre-trained streaming generation models, StreamGVE introduces dual-branch fast sampling with a self-attention bridge and cross-attention grounding/boosting to satisfy both sampling and conditioning requirements. We further propose source-oriented guidance to improve target-generation quality, and a visual prompting strategy to enhance editing flexibility and practicality. The method is effective, robust, and generalizable across different models. Extensive experiments on diverse video editing tasks show that StreamGVE consistently outperforms existing approaches, even in few-step settings with minimal time cost.
format Preprint
id arxiv_https___arxiv_org_abs_2605_21466
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle StreamGVE: Training-Free Video Editing via Few-Step Streaming Video Generation
Jiao, Guanlong
Zhang, Chenyangguang
Xian, Jia Jun Cheng
Zhang, Zewei
Liao, Renjie
Computer Vision and Pattern Recognition
Although existing video editing methods are generally feasible, they often require many costly iterations and still struggle to deliver high-quality yet satisfying editing results. We attribute this limitation to the prevalent data-to-data paradigm, which is less compatible with modern generative models than noise-to-data generation. To address this gap, we revisit video editing from a noise-to-data perspective and propose Streaming-Generation-based Video Editing (StreamGVE), which preserves few-step sampling while seamlessly injecting source-video conditions. Built on pre-trained streaming generation models, StreamGVE introduces dual-branch fast sampling with a self-attention bridge and cross-attention grounding/boosting to satisfy both sampling and conditioning requirements. We further propose source-oriented guidance to improve target-generation quality, and a visual prompting strategy to enhance editing flexibility and practicality. The method is effective, robust, and generalizable across different models. Extensive experiments on diverse video editing tasks show that StreamGVE consistently outperforms existing approaches, even in few-step settings with minimal time cost.
title StreamGVE: Training-Free Video Editing via Few-Step Streaming Video Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.21466