DreamSwapV: Mask-guided Subject Swapping for Any Customized Video Editing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Weitao, Wang, Zichen, Shen, Hongdeng, Lu, Yulei, Fan, Xirui, Wu, Suhui, Zhang, Jun, Wang, Haoqian, Zhang, Hao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908496192077824
author Wang, Weitao
Wang, Zichen
Shen, Hongdeng
Lu, Yulei
Fan, Xirui
Wu, Suhui
Zhang, Jun
Wang, Haoqian
Zhang, Hao
author_facet Wang, Weitao
Wang, Zichen
Shen, Hongdeng
Lu, Yulei
Fan, Xirui
Wu, Suhui
Zhang, Jun
Wang, Haoqian
Zhang, Hao
contents With the rapid progress of video generation, demand for customized video editing is surging, where subject swapping constitutes a key component yet remains under-explored. Prevailing swapping approaches either specialize in narrow domains--such as human-body animation or hand-object interaction--or rely on some indirect editing paradigm or ambiguous text prompts that compromise final fidelity. In this paper, we propose DreamSwapV, a mask-guided, subject-agnostic, end-to-end framework that swaps any subject in any video for customization with a user-specified mask and reference image. To inject fine-grained guidance, we introduce multiple conditions and a dedicated condition fusion module that integrates them efficiently. In addition, an adaptive mask strategy is designed to accommodate subjects of varying scales and attributes, further improving interactions between the swapped subject and its surrounding context. Through our elaborate two-phase dataset construction and training scheme, our DreamSwapV outperforms existing methods, as validated by comprehensive experiments on VBench indicators and our first introduced DreamSwapV-Benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14465
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DreamSwapV: Mask-guided Subject Swapping for Any Customized Video Editing
Wang, Weitao
Wang, Zichen
Shen, Hongdeng
Lu, Yulei
Fan, Xirui
Wu, Suhui
Zhang, Jun
Wang, Haoqian
Zhang, Hao
Computer Vision and Pattern Recognition
With the rapid progress of video generation, demand for customized video editing is surging, where subject swapping constitutes a key component yet remains under-explored. Prevailing swapping approaches either specialize in narrow domains--such as human-body animation or hand-object interaction--or rely on some indirect editing paradigm or ambiguous text prompts that compromise final fidelity. In this paper, we propose DreamSwapV, a mask-guided, subject-agnostic, end-to-end framework that swaps any subject in any video for customization with a user-specified mask and reference image. To inject fine-grained guidance, we introduce multiple conditions and a dedicated condition fusion module that integrates them efficiently. In addition, an adaptive mask strategy is designed to accommodate subjects of varying scales and attributes, further improving interactions between the swapped subject and its surrounding context. Through our elaborate two-phase dataset construction and training scheme, our DreamSwapV outperforms existing methods, as validated by comprehensive experiments on VBench indicators and our first introduced DreamSwapV-Benchmark.
title DreamSwapV: Mask-guided Subject Swapping for Any Customized Video Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.14465