FC-VFI: Faithful and Consistent Video Frame Interpolation for High-FPS Slow Motion Video Generation
This work provides a significant improvement in video frame interpolation quality for users and applications requiring high-fidelity slow-motion video generation, particularly for high-resolution and high-frame-rate content.
This paper addresses the challenge of generating high-fidelity slow-motion videos using video frame interpolation, specifically for 4x and 8x interpolation, boosting frame rates from 30 FPS to 120 and 240 FPS at 2560x1440 resolution. The authors developed FC-VFI, a method that preserves visual fidelity and motion consistency by introducing a temporal modeling strategy on latent sequences and leveraging semantic matching lines for structure-aware motion guidance.
Large pre-trained video diffusion models excel in video frame interpolation but struggle to generate high fidelity frames due to reliance on intrinsic generative priors, limiting detail preservation from start and end frames. Existing methods often depend on motion control for temporal consistency, yet dense optical flow is error-prone, and sparse points lack structural context. In this paper, we propose FC-VFI for faithful and consistent video frame interpolation, supporting \(4\times\)x and \(8\times\) interpolation, boosting frame rates from 30 FPS to 120 and 240 FPS at \(2560\times 1440\)resolution while preserving visual fidelity and motion consistency. We introduce a temporal modeling strategy on the latent sequences to inherit fidelity cues from start and end frames and leverage semantic matching lines for structure-aware motion guidance, improving motion consistency. Furthermore, we propose a temporal difference loss to mitigate temporal inconsistencies. Extensive experiments show FC-VFI achieves high performance and structural integrity across diverse scenarios.