FC-VFI: Faithful and Consistent Video Frame Interpolation for High-FPS Slow Motion Video Generation

TL;DR

FC-VFI is a novel video frame interpolation method that significantly boosts frame rates while maintaining high fidelity and motion consistency, using semantic matching and temporal difference loss.

Contribution

The paper introduces FC-VFI, a new approach that enhances high-FPS slow motion video generation with structure-aware motion guidance and temporal modeling.

Findings

Supports 4x and 8x interpolation at high resolution

Achieves superior visual fidelity and motion consistency

Outperforms existing methods across diverse scenarios

Abstract

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.