VFIMamba: Video Frame Interpolation with State Space Models

TL;DR

VFIMamba introduces a novel video frame interpolation method leveraging state space models for efficient, dynamic, and high-quality intermediate frame generation, especially excelling in high-resolution videos.

Contribution

It proposes the Mixed-SSM Block and a curriculum learning strategy to enhance inter-frame modeling using S6 models, achieving state-of-the-art results.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Improves PSNR by 0.80 dB on 4K frames.

Efficiently models long-range temporal dependencies.

Abstract

Inter-frame modeling is pivotal in generating intermediate frames for video frame interpolation (VFI). Current approaches predominantly rely on convolution or attention-based models, which often either lack sufficient receptive fields or entail significant computational overheads. Recently, Selective State Space Models (S6) have emerged, tailored specifically for long sequence modeling, offering both linear complexity and data-dependent modeling capabilities. In this paper, we propose VFIMamba, a novel frame interpolation method for efficient and dynamic inter-frame modeling by harnessing the S6 model. Our approach introduces the Mixed-SSM Block (MSB), which initially rearranges tokens from adjacent frames in an interleaved fashion and subsequently applies multi-directional S6 modeling. This design facilitates the efficient transmission of information across frames while upholding linear complexity. Furthermore, we introduce a novel curriculum learning strategy that progressively cultivates proficiency in modeling inter-frame dynamics across varying motion magnitudes, fully unleashing the potential of the S6 model. Experimental findings showcase that our method attains state-of-the-art performance across diverse benchmarks, particularly excelling in high-resolution scenarios. In particular, on the X-TEST dataset, VFIMamba demonstrates a noteworthy improvement of 0.80 dB for 4K frames and 0.96 dB for 2K frames.