Saved in:
Bibliographic Details
Main Authors: Gao, Wenshuo, Lan, Xicheng, Yang, Shuai
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.07472
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912578279571456
author Gao, Wenshuo
Lan, Xicheng
Yang, Shuai
author_facet Gao, Wenshuo
Lan, Xicheng
Yang, Shuai
contents Despite the rapid advancements in video generation technology, creating high-quality videos that precisely align with user intentions remains a significant challenge. Existing methods often fail to achieve fine-grained control over video details, limiting their practical applicability. We introduce ANYPORTAL, a novel zero-shot framework for video background replacement that leverages pre-trained diffusion models. Our framework collaboratively integrates the temporal prior of video diffusion models with the relighting capabilities of image diffusion models in a zero-shot setting. To address the critical challenge of foreground consistency, we propose a Refinement Projection Algorithm, which enables pixel-level detail manipulation to ensure precise foreground preservation. ANYPORTAL is training-free and overcomes the challenges of achieving foreground consistency and temporally coherent relighting. Experimental results demonstrate that ANYPORTAL achieves high-quality results on consumer-grade GPUs, offering a practical and efficient solution for video content creation and editing.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07472
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ANYPORTAL: Zero-Shot Consistent Video Background Replacement
Gao, Wenshuo
Lan, Xicheng
Yang, Shuai
Computer Vision and Pattern Recognition
Despite the rapid advancements in video generation technology, creating high-quality videos that precisely align with user intentions remains a significant challenge. Existing methods often fail to achieve fine-grained control over video details, limiting their practical applicability. We introduce ANYPORTAL, a novel zero-shot framework for video background replacement that leverages pre-trained diffusion models. Our framework collaboratively integrates the temporal prior of video diffusion models with the relighting capabilities of image diffusion models in a zero-shot setting. To address the critical challenge of foreground consistency, we propose a Refinement Projection Algorithm, which enables pixel-level detail manipulation to ensure precise foreground preservation. ANYPORTAL is training-free and overcomes the challenges of achieving foreground consistency and temporally coherent relighting. Experimental results demonstrate that ANYPORTAL achieves high-quality results on consumer-grade GPUs, offering a practical and efficient solution for video content creation and editing.
title ANYPORTAL: Zero-Shot Consistent Video Background Replacement
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.07472