arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.16144cs.CVcs.MM
收藏

基于流 Transformer 的视频帧插值

Video Frame Interpolation with Flow Transformer

Nanjing University of Aeronautics and Astronautics(南京航空航天大学)

Pan Gao, Haoyue Tian, Jie Qin

AI总结:

针对卷积视频帧插值丢失细节的问题,提出流 Transformer,将光流运动动力学融入时间自注意力机制并结合多尺度架构,在三个基准上实现了更优的视觉质量。

摘要:

随着卷积神经网络的发展,视频帧插值得到了积极的研究。然而,由于卷积中核权重共享的内在限制,其生成的插值帧可能会丢失细节。相比之下,Transformer 中的注意力机制能更好地区分每个像素的贡献,还能捕获长距离像素依赖关系,为视频插值提供了巨大潜力。尽管如此,原始 Transformer 通常用于 2D 图像;如何开发一个考虑时间自注意力的基于 Transformer 的框架用于视频帧插值仍是一个开放问题。在本文中,我们提出视频帧插值流 Transformer,将来自光流的运动动力学整合到自注意力机制中。具体而言,我们设计了一个流 Transformer 块,在流的引导下于匹配的局部区域内计算时间自注意力,使我们的框架适合插值大运动帧,同时保持合理的低复杂度。此外,我们构建了一个多尺度架构以考虑多尺度运动,进一步提升整体性能。在三个基准上的大量实验表明,所提方法能生成比现有最先进方法视觉质量更好的插值帧。

英文摘要:

Video frame interpolation has been actively studied with the development of convolutional neural networks. However, due to the intrinsic limitations of kernel weight sharing in convolution, the interpolated frame generated by it may lose details. In contrast, the attention mechanism in Transformer can better distinguish the contribution of each pixel, and it can also capture long-range pixel dependencies, which provides great potential for video interpolation. Nevertheless, the original Transformer is commonly used for 2D images; how to develop a Transformer-based framework with consideration of temporal self-attention for video frame interpolation remains an open issue. In this paper, we propose Video Frame Interpolation Flow Transformer to incorporate motion dynamics from optical flows into the self-attention mechanism. Specifically, we design a Flow Transformer Block that calculates the temporal self-attention in a matched local area with the guidance of flow, making our framework suitable for interpolating frames with large motion while maintaining reasonably low complexity. In addition, we construct a multi-scale architecture to account for multi-scale motion, further improving the overall performance. Extensive experiments on three benchmarks demonstrate that the proposed method can generate interpolated frames with better visual quality than state-of-the-art methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑