English

Flow-Guided Diffusion for Video Inpainting

Computer Vision and Pattern Recognition 2025-01-24 v2

Abstract

Video inpainting has been challenged by complex scenarios like large movements and low-light conditions. Current methods, including emerging diffusion models, face limitations in quality and efficiency. This paper introduces the Flow-Guided Diffusion model for Video Inpainting (FGDVI), a novel approach that significantly enhances temporal consistency and inpainting quality via reusing an off-the-shelf image generation diffusion model. We employ optical flow for precise one-step latent propagation and introduces a model-agnostic flow-guided latent interpolation technique. This technique expedites denoising, seamlessly integrating with any Video Diffusion Model (VDM) without additional training. Our FGDVI demonstrates a remarkable 10% improvement in flow warping error E_warp over existing state-of-the-art methods. Our comprehensive experiments validate superior performance of FGDVI, offering a promising direction for advanced video inpainting. The code and detailed results will be publicly available in https://github.com/NevSNev/FGDVI.

Keywords

Cite

@article{arxiv.2311.15368,
  title  = {Flow-Guided Diffusion for Video Inpainting},
  author = {Bohai Gu and Yongsheng Yu and Heng Fan and Libo Zhang},
  journal= {arXiv preprint arXiv:2311.15368},
  year   = {2025}
}

Comments

This paper has been withdrawn as a new iteration of the work has been developed, which includes significant improvements and refinements based on this submission. The withdrawal is made to ensure academic integrity and compliance with publication standards. If you are interested, please refer to the updated work at arXiv:2412.00857

R2 v1 2026-06-28T13:31:55.078Z