arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 2201.11407cs.CVcs.AI
收藏

基于空时卷积的视频帧内插非线性运动估计

Non-linear Motion Estimation for Video Frame Interpolation using Space-time Convolutions

Indian Institute of Technology Madras(印度理工学院马德拉斯分校)

Saikat Dutta, Arulkumar Subramaniam, Anurag Mittal

摘要:

视频帧内插的目的是在视频中的两个连续帧之间合成一个或多个帧。它具有广泛的应用,包括慢动作视频生成,帧速率提升和开发视频编解码器。一些较早的作品通过假设视频帧之间的每像素线性运动来解决这个问题。然而,对象通常在实域中遵循非线性运动模式,并且一些最近的方法试图通过非线性模型(例如,二次的)。二次模型也可能是不准确的,特别是在运动随时间的不连续性(即突然的急拉)和遮挡的情况下,其中一些流动信息可能是无效的或不准确的。在我们的论文中,我们提出了近似的每像素的运动,使用时空卷积网络,能够自适应地选择要使用的运动模型。具体来说,我们能够在线性和二次模型之间进行软切换。为此,我们在双向光流和遮挡图上使用端到端3D CNN编码器-解码器架构来估计每个像素的非线性运动模型。此外,采用运动细化模块来细化非线性运动,并且通过利用所估计的每像素运动对相邻帧进行简单扭曲来估计内插帧。通过一组综合实验,我们验证了我们的模型的有效性,并表明我们的方法优于最先进的算法在四个数据集(Vimeo,DAVIS,HD和GoPro)。

英文摘要:

Video frame interpolation aims to synthesize one or multiple frames between two consecutive frames in a video. It has a wide range of applications including slow-motion video generation, frame-rate up-scaling and developing video codecs. Some older works tackled this problem by assuming per-pixel linear motion between video frames. However, objects often follow a non-linear motion pattern in the real domain and some recent methods attempt to model per-pixel motion by non-linear models (e.g., quadratic). A quadratic model can also be inaccurate, especially in the case of motion discontinuities over time (i.e. sudden jerks) and occlusions, where some of the flow information may be invalid or inaccurate. In our paper, we propose to approximate the per-pixel motion using a space-time convolution network that is able to adaptively select the motion model to be used. Specifically, we are able to softly switch between a linear and a quadratic model. Towards this end, we use an end-to-end 3D CNN encoder-decoder architecture over bidirectional optical flows and occlusion maps to estimate the non-linear motion model of each pixel. Further, a motion refinement module is employed to refine the non-linear motion and the interpolated frames are estimated by a simple warping of the neighboring frames with the estimated per-pixel motion. Through a set of comprehensive experiments, we validate the effectiveness of our model and show that our method outperforms state-of-the-art algorithms on four datasets (Vimeo, DAVIS, HD and GoPro).

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。

↑