DreamSwapV: Mask-guided Subject Swapping for Any Customized Video Editing
This addresses the need for flexible and high-fidelity subject swapping in video editing, which is incremental as it builds on existing video generation methods but introduces novel guidance and training techniques.
The paper tackles the problem of subject swapping in customized video editing by proposing DreamSwapV, a mask-guided framework that swaps any subject in any video using a user-specified mask and reference image, achieving superior performance as validated by VBench indicators and a new benchmark.
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.