Flow-Guided Diffusion for Video Inpainting
This work addresses video inpainting for applications requiring temporal consistency, but it is incremental as it builds on existing diffusion models with a novel integration technique.
The paper tackled video inpainting challenges like large movements and low-light conditions by introducing the Flow-Guided Diffusion model for Video Inpainting (FGDVI), which achieved a 10% improvement in flow warping error over state-of-the-art methods.
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.