1. [Publications](/publications)
2. HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformers

 # HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformers

  ![](/sites/default/files/styles/wide/public/publications/qualitative_prompting_editing.jpg?itok=FAs8S8IO)

 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.

 ## Authors

Jing Yang (NVIDIA, University of Southern California)

Mayoore Jaiswal (NVIDIA)

Zian Wang (NVIDIA)

Xiao Steven Zeng (NVIDIA)

Yajie Zhao (University of Southern California)

Rochelle Pereira (NVIDIA)

Jianyuan Min (NVIDIA)

 ## Publication Date

Friday, August 14, 2026

 ## Published in

[Arxiv](https://arxiv.org/abs/2606.29095)

 ## Research Area

[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

[Computational Photography and Imaging](/research-area/computational-photography-imaging)

[Computer Graphics](/research-area/computer-graphics)

[Computer Vision](/research-area/computer-vision)

[Generative AI](/research-area/generative-ai)

 ## External Links

[Project Page](https://research.nvidia.com/labs/sil/projects/horizonrelight/)