Coherent Video Inpainting Using Optical Flow-Guided Efficient Diffusion
This addresses video inpainting for content generation applications, representing an incremental improvement over existing diffusion-based approaches.
The paper tackles the problem of temporal inconsistency and computational inefficiency in diffusion-based video inpainting by proposing FloED, a framework using optical flow guidance and efficient mechanisms. Results show it outperforms state-of-the-art methods in quality and efficiency on background restoration and object removal tasks.
The text-guided video inpainting technique has significantly improved the performance of content generation applications. A recent family for these improvements uses diffusion models, which have become essential for achieving high-quality video inpainting results, yet they still face performance bottlenecks in temporal consistency and computational efficiency. This motivates us to propose a new video inpainting framework using optical Flow-guided Efficient Diffusion (FloED) for higher video coherence. Specifically, FloED employs a dual-branch architecture, where the time-agnostic flow branch restores corrupted flow first, and the multi-scale flow adapters provide motion guidance to the main inpainting branch. Besides, a training-free latent interpolation method is proposed to accelerate the multi-step denoising process using flow warping. With the flow attention cache mechanism, FLoED efficiently reduces the computational cost of incorporating optical flow. Extensive experiments on background restoration and object removal tasks show that FloED outperforms state-of-the-art diffusion-based methods in both quality and efficiency. Our codes and models will be made publicly available.