无需训练的视频光影重制与背景替换新方法
FlowPortal: Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement
- 基于残差修正光流，实现无训练条件下的精准编辑
- 在时间连贯性与光照自然度上优于现有方法
- 适合影视制作与创意媒体领域快速原型设计
视频光影重制与背景替换是电影制作和创意媒体中的关键挑战。现有方法难以兼顾时间一致性、空间保真度和光照自然性。为此，我们提出FlowPortal，一种全新的无训练光流视频重制框架。核心创新在于残差修正光流机制，将标准光流模型转化为编辑模型，在输入条件相同时可实现完美重建，不同条件下则保证忠实的光影重制，从而获得高结构一致性。该机制通过解耦条件设计实现精确光照控制，并引入高频信息传递机制以保留细节。此外，掩码策略将前景光影重制与纯背景生成过程分离。实验表明，FlowPortal在时间连贯性、结构保持和光照真实感方面均表现优异，同时具备高效率。项目页面：https://gaowenshuo.github.io/FlowPortalProject/
原文摘要 · Abstract (English)
Video relighting with background replacement is a challenging task critical for applications in film production and creative media. Existing methods struggle to balance temporal consistency, spatial fidelity, and illumination naturalness. To address these issues, we introduce FlowPortal, a novel training-free flow-based video relighting framework. Our core innovation is a Residual-Corrected Flow mechanism that transforms a standard flow-based model into an editing model, guaranteeing perfect reconstruction when input conditions are identical and enabling faithful relighting when they differ, resulting in high structural consistency. This is further enhanced by a Decoupled Condition Design for precise lighting control and a High-Frequency Transfer mechanism for detail preservation. Additionally, a masking strategy isolates foreground relighting from background pure generation process. Experiments demonstrate that FlowPortal achieves superior performance in temporal coherence, structural preservation, and lighting realism, while maintaining high efficiency. Project Page: https://gaowenshuo.github.io/FlowPortalProject/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。