Re-Attentional Controllable Video Diffusion Editing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yuanzhi, Li, Yong, Liu, Mengyi, Zhang, Xiaoya, Liu, Xin, Cui, Zhen, Chan, Antoni B.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913614018904064
author Wang, Yuanzhi
Li, Yong
Liu, Mengyi
Zhang, Xiaoya
Liu, Xin
Cui, Zhen
Chan, Antoni B.
author_facet Wang, Yuanzhi
Li, Yong
Liu, Mengyi
Zhang, Xiaoya
Liu, Xin
Cui, Zhen
Chan, Antoni B.
contents Editing videos with textual guidance has garnered popularity due to its streamlined process which mandates users to solely edit the text prompt corresponding to the source video. Recent studies have explored and exploited large-scale text-to-image diffusion models for text-guided video editing, resulting in remarkable video editing capabilities. However, they may still suffer from some limitations such as mislocated objects, incorrect number of objects. Therefore, the controllability of video editing remains a formidable challenge. In this paper, we aim to challenge the above limitations by proposing a Re-Attentional Controllable Video Diffusion Editing (ReAtCo) method. Specially, to align the spatial placement of the target objects with the edited text prompt in a training-free manner, we propose a Re-Attentional Diffusion (RAD) to refocus the cross-attention activation responses between the edited text prompt and the target video during the denoising stage, resulting in a spatially location-aligned and semantically high-fidelity manipulated video. In particular, to faithfully preserve the invariant region content with less border artifacts, we propose an Invariant Region-guided Joint Sampling (IRJS) strategy to mitigate the intrinsic sampling errors w.r.t the invariant regions at each denoising timestep and constrain the generated content to be harmonized with the invariant region content. Experimental results verify that ReAtCo consistently improves the controllability of video diffusion editing and achieves superior video editing performance.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11710
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Re-Attentional Controllable Video Diffusion Editing
Wang, Yuanzhi
Li, Yong
Liu, Mengyi
Zhang, Xiaoya
Liu, Xin
Cui, Zhen
Chan, Antoni B.
Computer Vision and Pattern Recognition
Artificial Intelligence
Editing videos with textual guidance has garnered popularity due to its streamlined process which mandates users to solely edit the text prompt corresponding to the source video. Recent studies have explored and exploited large-scale text-to-image diffusion models for text-guided video editing, resulting in remarkable video editing capabilities. However, they may still suffer from some limitations such as mislocated objects, incorrect number of objects. Therefore, the controllability of video editing remains a formidable challenge. In this paper, we aim to challenge the above limitations by proposing a Re-Attentional Controllable Video Diffusion Editing (ReAtCo) method. Specially, to align the spatial placement of the target objects with the edited text prompt in a training-free manner, we propose a Re-Attentional Diffusion (RAD) to refocus the cross-attention activation responses between the edited text prompt and the target video during the denoising stage, resulting in a spatially location-aligned and semantically high-fidelity manipulated video. In particular, to faithfully preserve the invariant region content with less border artifacts, we propose an Invariant Region-guided Joint Sampling (IRJS) strategy to mitigate the intrinsic sampling errors w.r.t the invariant regions at each denoising timestep and constrain the generated content to be harmonized with the invariant region content. Experimental results verify that ReAtCo consistently improves the controllability of video diffusion editing and achieves superior video editing performance.
title Re-Attentional Controllable Video Diffusion Editing
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.11710