用扩散模型实现长视频一致重光照，解决片段拼接时的闪烁问题。
HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformers
- 将重光照建模为时序条件的潜在域转换，跨片段传递目标域隐状态。
- 通过掩码自条件训练，使模型能从被遮蔽的上下文继续生成，提升连续性。
- 引入热启动提示锚点，支持基于提示的可控重光照，适合影视后期场景。
基于扩散模型的视频重光照可从单个输入视频实现可控重光照，但现代视频扩散主干网络通常在短片段上训练，并通过分块滑动窗口推理应用于长时序视频，常导致片段边界处的时间不连续性。我们提出将长时序重光照重新建模为时序条件的潜在域转换。通过跨边界传播目标域隐状态，并利用掩码目标域自条件训练，使模型能够从被遮蔽的时序上下文中学习延续生成行为。此外，我们引入热启动提示，使用可控生成模型提供的重光照提示锚点，建立初始目标域状态，并构建通用的基于提示的重光照接口。在真实世界长时序视频上的实验表明，时间一致性显著提升，片段边界伪影大幅减少，跨片段的意外外观变化也得到有效抑制。
原文摘要 · Abstract (English)
Diffusion-based video relighting enables controllable relighting from a single input video, but modern video diffusion backbones are trained on short clips and applied to long-horizon videos through chunked sliding-window inference, often causing temporal discontinuities at chunk boundaries. We address this by reframing long-horizon relighting as \emph{temporally conditioned latent domain translation}. Our framework enforces cross-chunk continuity by propagating target-domain latents across boundaries and makes this behavior learnable using \emph{masked target-domain self-conditioning}, training the model to continue from temporally masked propagated context. We further introduce \emph{warm-start prompting} with a relit prompt anchor from a controllable generative model, which establishes the initial target-domain state and creates a general interface for prompt-based relighting. Experiments on in-the-wild long-horizon videos show markedly improved temporal consistency, with chunk-boundary artifacts largely reduced and unwanted appearance changes across chunks greatly suppressed.
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。