EUVIMEDEUVIMED entdecken
Crossref

RelightFlow: An Inversion-Free Video Relighting Model via Dual-Trajectory Diffusion Editing

Yukun Wang, Qiyuan Zhang, Qi Zhang, Longguang Wang, Yulan Guo

IEEE Transactions on Circuits and Systems for Video Technology · 2026-08 · 36 (8) · 11802-11816

DOI: 10.1109/tcsvt.2026.3683103 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-08. Verfasst von Yukun Wang und 4 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Gefördert von: Guangdong Science and Technology Program, National Natural Science Foundation of China, Basic and Applied Basic Research Foundation of Guangdong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Video relighting is a fundamental task with wide-ranging applications in contemporary visual computing, including film production, immersive virtual reality, augmented reality, and interactive digital worlds. Its objective is to generate temporally stable lighting effects while preserving the structural integrity, visual appearance, and intrinsic physical properties of objects in the source video. Recent studies combined image relighting models with video diffusion models, achieving notable progress in training-free video relighting. However, these methods rely on mapping noisy latents back to the pixel space during the relighting process, leading to degraded fidelity, consistency, and stability. In this work, we propose RelightFlow, a training-free video relighting framework built upon a flow-matching-based video DiT model, which requires neither inversion nor additional training, obtaining more feasible and robust relighting effects. Specifically, we first design a detail-preserving relighting module coupled with an interpolation trajectory, which injects stable lighting cues in the early generation stages while maintaining fine spatial details. Next, we develop a temporally consistent relighting module to form a flow-editing trajectory, leveraging the velocity fields predicted by the video DiT model to enhance temporal coherence. Finally, we introduce a dynamic fusion strategy that adaptively integrates these two trajectories to balance relighting intensity and temporal stability. Extensive experiments demonstrate that RelightFlow achieves high-quality video relighting with stable relighting intensity, superior fidelity, and temporal consistency. The code are provided in https://github.com/Yukun66/RelightFlow

Förderung

  • Guangdong Science and Technology Program
  • National Natural Science Foundation of China
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Special Financial Grant from China Postdoctoral Science Foundation
  • Science and Technology Planning Project of Key Laboratory of Advanced IntelliSense Technology, Guangdong Science and Technology Department

Zitieren

APA

Wang, Y., Zhang, Q., Zhang, Q., Wang, L., & Guo, Y. (2026). RelightFlow: An Inversion-Free Video Relighting Model via Dual-Trajectory Diffusion Editing. IEEE Transactions on Circuits and Systems for Video Technology, 36(8), 11802-11816. https://doi.org/10.1109/tcsvt.2026.3683103

Vancouver

Wang Y, Zhang Q, Zhang Q, Wang L, Guo Y. RelightFlow: An Inversion-Free Video Relighting Model via Dual-Trajectory Diffusion Editing. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(8):11802-11816. doi:10.1109/tcsvt.2026.3683103

BibTeX
@article{Wang2026,
  author = {Wang, Yukun and Zhang, Qiyuan and Zhang, Qi and Wang, Longguang and Guo, Yulan},
  title = {RelightFlow: An Inversion-Free Video Relighting Model via Dual-Trajectory Diffusion Editing},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {8},
  pages = {11802--11816},
  doi = {10.1109/tcsvt.2026.3683103}
}
Kostenlos starten →