我们提出了一种用于视频帧插值(VFI)的实时中流估计算法。许多最近的基于流的VFI方法首先估计双向光学流,然后缩放并将它们倒转到近似中间流动,导致运动边界上的伪像。RIFE使用名为IFNET的神经网络,可以直接估计中间流量从粗细流,速度更好。我们设计了一种用于训练中间流动模型的特权蒸馏方案,这导致了大的性能改善。Rife不依赖于预先训练的光流模型,可以支持任意时间的帧插值。实验表明,普里埃雷在若干公共基准上实现了最先进的表现。\ url {https://github.com/hzwer/arxiv2020-rife}。
translated by 谷歌翻译
视频框架合成由插值和外推组成,是一种必不可少的视频处理技术,可应用于各种情况。但是,大多数现有方法无法处理小物体或大型运动,尤其是在高分辨率视频(例如4K视频)中。为了消除此类局限性,我们引入了基于流动帧合成的邻居对应匹配(NCM)算法。由于当前的帧在视频框架合成中不可用,因此NCM以当前框架的方式进行,以在每个像素的空间型社区中建立多尺度对应关系。基于NCM的强大运动表示能力,我们进一步建议在异质的粗到细节方案中估算框架合成的中间流。具体而言,粗尺度模块旨在利用邻居的对应关系来捕获大型运动,而细尺度模块在计算上更有效地加快了估计过程。两个模块都经过逐步训练,以消除培训数据集和现实世界视频之间的分辨率差距。实验结果表明,NCM在多个基准测试中实现了最先进的性能。此外,NCM可以应用于各种实践场景,例如视频压缩,以实现更好的性能。
translated by 谷歌翻译
我们为基于运动的视频框架插值提供了一种新颖的简单而有效的算法。现有的基于运动的插值方法通常依赖于预先训练的光流模型或基于U-NET的金字塔网络进行运动估计,该运动估计要么具有较大的模型大小或有限的处理复合物和大型运动案例的容量。在这项工作中,通过仔细整合了中间方向的前射击,轻质特征编码器和相关量为金字塔复发框架,我们得出一个紧凑的模型,以同时估计输入帧之间的双向运动。它的尺寸比PWC-NET小15倍,但可以更可靠,更灵活地处理具有挑战性的运动案例。基于估计的双向运动,我们向前射击输入帧及其上下文特征到中间帧,并采用合成网络来估算扭曲表示的中间帧。我们的方法在广泛的视频框架插值基准测试中实现了出色的性能。代码将很快可用。
translated by 谷歌翻译
Flow-guide synthesis provides a common framework for frame interpolation, where optical flow is typically estimated by a pyramid network, and then leveraged to guide a synthesis network to generate intermediate frames between input frames. In this paper, we present UPR-Net, a novel Unified Pyramid Recurrent Network for frame interpolation. Cast in a flexible pyramid framework, UPR-Net exploits lightweight recurrent modules for both bi-directional flow estimation and intermediate frame synthesis. At each pyramid level, it leverages estimated bi-directional flow to generate forward-warped representations for frame synthesis; across pyramid levels, it enables iterative refinement for both optical flow and intermediate frame. In particular, we show that our iterative synthesis can significantly improve the robustness of frame interpolation on large motion cases. Despite being extremely lightweight (1.7M parameters), UPR-Net achieves excellent performance on a large range of benchmarks. Code will be available soon.
translated by 谷歌翻译
我们提出了一种称为基于DNN的基于DNN的框架,称为基于增强的相关匹配的视频帧插值网络,以支持4K的高分辨率,其具有大规模的运动和遮挡。考虑到根据分辨率的网络模型的可扩展性,所提出的方案采用经常性金字塔架构,该架构分享每个金字塔层之间的参数进行光学流量估计。在所提出的流程估计中,通过追踪具有最大相关性的位置来递归地改进光学流。基于前扭曲的相关匹配可以通过排除遮挡区域周围的错误扭曲特征来提高流量更新的准确性。基于最终双向流动,使用翘曲和混合网络合成任意时间位置的中间帧,通过细化网络进一步改善。实验结果表明,所提出的方案在4K视频数据和低分辨率基准数据集中占据了之前的工作,以及具有最小型号参数的客观和主观质量。
translated by 谷歌翻译
translated by 谷歌翻译
Given two consecutive frames, video interpolation aims at generating intermediate frame(s) to form both spatially and temporally coherent video sequences. While most existing methods focus on single-frame interpolation, we propose an end-to-end convolutional neural network for variable-length multi-frame video interpolation, where the motion interpretation and occlusion reasoning are jointly modeled. We start by computing bi-directional optical flow between the input images using a U-Net architecture. These flows are then linearly combined at each time step to approximate the intermediate bi-directional optical flows. These approximate flows, however, only work well in locally smooth regions and produce artifacts around motion boundaries. To address this shortcoming, we employ another U-Net to refine the approximated flow and also predict soft visibility maps. Finally, the two input images are warped and linearly fused to form each intermediate frame. By applying the visibility maps to the warped images before fusion, we exclude the contribution of occluded pixels to the interpolated intermediate frame to avoid artifacts. Since none of our learned network parameters are time-dependent, our approach is able to produce as many intermediate frames as needed. To train our network, we use 1,132 240-fps video clips, containing 300K individual video frames. Experimental results on several datasets, predicting different numbers of interpolated frames, demonstrate that our approach performs consistently better than existing methods.
translated by 谷歌翻译
视频框架插值是一项经典且具有挑战性的低级计算机视觉任务。最近,基于深度学习的方法取得了令人印象深刻的结果,并且已证明基于光流的方法可以合成具有更高质量的帧。但是,大多数基于流动的方法都假设两个输入帧之间具有恒定速度的线轨迹。只有一点点工作可以使用曲线轨迹执行预测,但这需要两个以上的框架作为输入来估计加速度,这需要更多的时间和内存才能执行。为了解决这个问题,我们提出了一个基于ARC轨迹的模型(ATCA),该模型仅从连续两个帧中就可以在前学习运动,而且轻量级。实验表明,我们的方法的性能要比许多参数较少且推理速度更快的SOTA方法更好。
translated by 谷歌翻译
在本文中,我们提出了一种新颖的联合去钻头和多帧插值(DEMFI)框架,称为DEMFI-NET,该网球被准确地将较低帧速率的模糊视频以基于流动引导的更高帧速率转换为尖锐的视频基于关提性的相关性的特征借助于多帧插值(MFI)的借助于基于相关的特征Bolstering(FAC-FB)模块和递归升压(RB)。 DEMFI-NET联合执行DeBlurring和MFI,其中其基线版本执行与FAC-FB模块的基于特征流的翘曲,以获得尖锐插值的帧,也可以解置两个中心输入帧。此外,其扩展版本进一步提高了基于基于像素的RB的像素流的翘曲的联合任务性能。我们的FAC-FB模块在特征域中的模糊输入帧中有效地聚集了分布式模糊像素信息,以改善整体关节性能,这是计算上有效的,因为其细心的相关性仅聚焦。结果,与最近的SOTA方法相比,我们的DEMFI-Net实现了最先进的数据集,用于近期SOTA方法,用于脱孔和MFI。所有源代码包括预押德福网在https://github.com/jihyongoh/demfi上公开提供。
translated by 谷歌翻译
视频帧插值(VFI)目前是一个非常活跃的研究主题,具有跨越计算机视觉,后期生产和视频编码的应用程序。 VFI可能非常具有挑战性,特别是在含有大型运动,闭塞或动态纹理的序列中,现有方法未能提供感知鲁棒的插值性能。在这种情况下,我们基于时空多流量架构介绍了一种基于深度学习的VFI方法ST-MFNET。 ST-MFNET采用新的多尺度多流量预测器来估计多对一的中间流动,它们与传统的一对一光流组合以捕获大型和复杂的运动。为了增强各种纹理的插值性能,还用于在扩展时间窗口上模拟内容动态的3D CNN。此外,ST-MFNET已经在ST-GaN框架内培训,该框架最初是为纹理合成而开发的,目的是进一步提高感知插值质量。我们的方法已被全面评估 - 与十四个最先进的VFI算法相比 - 清楚地展示了ST-MFNET在各种和代表性测试数据集上始终如一地优于这些基准,在PSNR中具有显着的收益,用于案件在PSNR中高达1.09dB包括大型运动和动态纹理。项目页面:https://danielism97.github.io/st-mfnet。
translated by 谷歌翻译
Standard video frame interpolation methods first estimate optical flow between input frames and then synthesize an intermediate frame guided by motion. Recent ap-proaches merge these two steps into a single convolution process by convolving input frames with spatially adaptive kernels that account for motion and re-sampling simultaneously. These methods require large kernels to handle large motion, which limits the number of pixels whose kernels can be estimated at once due to the large memory demand. To address this problem, this paper formulates frame interpolation as local separable convolution over input frames using pairs of 1D kernels. Compared to regular 2D kernels, the 1D kernels require significantly fewer parameters to be estimated. Our method develops a deep fully convolutional neural network that takes two input frames and estimates pairs of 1D kernels for all pixels simultaneously. Since our method is able to estimate kernels and synthesizes the whole video frame at once, it allows for the incorporation of perceptual loss to train the neural network to produce visually pleasing frames. This deep neural network is trained end-to-end using widely available video data without any human annotation. Both qualitative and quantitative experiments show that our method provides a practical solution to high-quality video frame interpolation.
translated by 谷歌翻译
视频框架插值是一项艰巨的任务,这是由于不断变化的现实场景。先前的方法通常计算双向光流,然后在线性运动假设下预测中间光流,从而导致各向同性中间流量产生。随访研究通过估计的高阶运动信息和额外的帧获得各向异性调整。基于运动假设,它们的方法很难在真实场景中对复杂的运动进行建模。在本文中,我们提出了一种端到端训练方法A^2OF,用于视频框架插值,并通过事件驱动的各向异性调整光学流量调节。具体而言,我们使用事件为中间光流生成光流分布掩码,这可以对两个帧之间的复杂运动进行建模。我们提出的方法在视频框架插值中优于先前的方法,将基于事件的视频插值带到了更高的阶段。
translated by 谷歌翻译
Recently, flow-based frame interpolation methods have achieved great success by first modeling optical flow between target and input frames, and then building synthesis network for target frame generation. However, above cascaded architecture can lead to large model size and inference delay, hindering them from mobile and real-time applications. To solve this problem, we propose a novel Progressive Motion Context Refine Network (PMCRNet) to predict motion fields and image context jointly for higher efficiency. Different from others that directly synthesize target frame from deep feature, we explore to simplify frame interpolation task by borrowing existing texture from adjacent input frames, which means that decoder in each pyramid level of our PMCRNet only needs to update easier intermediate optical flow, occlusion merge mask and image residual. Moreover, we introduce a new annealed multi-scale reconstruction loss to better guide the learning process of this efficient PMCRNet. Experiments on multiple benchmarks show that proposed approaches not only achieve favorable quantitative and qualitative results but also reduces current model size and running time significantly.
translated by 谷歌翻译
现有的视频框架插值方法只能在给定的中间时间步骤中插值框架,例如1/2。在本文中,我们旨在探索一种更广泛的视频框架插值,该视频框架在任意时步。为此,我们考虑在元学习的帮助下以统一的方式处理不同的时间阶段。具体而言,我们开发了一个双元学习的帧插值框架,以通过上下文信息和光流的指导以及将时间步长为附带信息,将中间框架合成中间框架。首先,构建了一个内容感知的元学习流程模块,以提高基于输入帧的下采样版本的光流估计的准确性。其次,以精致的光流和时间步长为输入,运动吸引的元学习框架插值模块为在粗翘曲版本的特征图上使用的每个像素生成卷积内核,以生成输入的特征图上的每个像素生成预测帧的帧。广泛的定性和定量评估以及消融研究表明,通过以如此精心设计的方式在我们的框架中引入元学习,我们的方法不仅可以实现优于先进的框架插值方法,还可以实现优越的性能还拥有在任意时间步长以支持插值的扩展能力。
translated by 谷歌翻译
视频框架插值(VFI)旨在合成两个连续帧之间的中间框架。最先进的方法通常采用两步解决方案,其中包括1)通过基于流动的运动估计来生成本地光线的像素,2)将扭曲的像素混合以通过深神经合成网络形成全帧。但是,由于两个连续的帧不一致,新帧的扭曲功能通常不会对齐,这会导致扭曲和模糊的帧,尤其是在发生大型和复杂的运动时。为了解决这个问题,在本文中,我们提出了一种新颖的视频框架插值变压器(TTVFI)。特别是,我们以不一致的动作为查询令牌制定了扭曲的特征,并将运动轨迹中的相关区域从两个原始的连续帧中提出到键和值。在沿轨迹的相关令牌上学习了自我注意力,以通过端到端训练将原始特征融合到中间框架中。实验结果表明,我们的方法在四个广泛使用的VFI基准中优于其他最先进的方法。代码和预培训模型都将很快发布。
translated by 谷歌翻译
Recent works have shown that optical flow can be learned by deep networks from unlabelled image pairs based on brightness constancy assumption and smoothness prior. Current approaches additionally impose an augmentation regularization term for continual self-supervision, which has been proved to be effective on difficult matching regions. However, this method also amplify the inevitable mismatch in unsupervised setting, blocking the learning process towards optimal solution. To break the dilemma, we propose a novel mutual distillation framework to transfer reliable knowledge back and forth between the teacher and student networks for alternate improvement. Concretely, taking estimation of off-the-shelf unsupervised approach as pseudo labels, our insight locates at defining a confidence selection mechanism to extract relative good matches, and then add diverse data augmentation for distilling adequate and reliable knowledge from teacher to student. Thanks to the decouple nature of our method, we can choose a stronger student architecture for sufficient learning. Finally, better student prediction is adopted to transfer knowledge back to the efficient teacher without additional costs in real deployment. Rather than formulating it as a supervised task, we find that introducing an extra unsupervised term for multi-target learning achieves best final results. Extensive experiments show that our approach, termed MDFlow, achieves state-of-the-art real-time accuracy and generalization ability on challenging benchmarks. Code is available at https://github.com/ltkong218/MDFlow.
translated by 谷歌翻译
We address the problem of synthesizing new video frames in an existing video, either in-between existing frames (interpolation), or subsequent to them (extrapolation). This problem is challenging because video appearance and motion can be highly complex. Traditional optical-flow-based solutions often fail where flow estimation is challenging, while newer neural-network-based methods that hallucinate pixel values directly often produce blurry results. We combine the advantages of these two methods by training a deep network that learns to synthesize video frames by flowing pixel values from existing ones, which we call deep voxel flow. Our method requires no human supervision, and any video can be used as training data by dropping, and then learning to predict, existing frames. The technique is efficient, and can be applied at any video resolution. We demonstrate that our method produces results that both quantitatively and qualitatively improve upon the state-ofthe-art.
translated by 谷歌翻译
视频框架插值(VFI)旨在通过从双向历史参考文献中扭曲可学习的动作来产生预测帧。大多数现有的作品都利用时空语义信息提取器来实现运动估计和插值建模,考虑到产生的中间运动的实际机械合理性,没有足够的考虑。在本文中,我们将VFI重新制定为多变量的非线性(MNL)回归问题,并提出了联合非线性运动回归(JNMR)策略来模拟框架间的复杂运动。为了建立MNL回归,采用ConvlSTM来构建时间维度的完整运动的分布。目标框架和多个参考帧之间的运动相关性可以通过建模的分布进行回归。此外,功能学习网络旨在为MNL回归建模进行优化。进一步进行了一个粗到精细的合成增强模块,以通过重复回归和插值来学习不同分辨率的视觉动力学。框架插值上的高度竞争性实验结果表明,与最先进的性能相比,有效性和显着提高,以及复杂运动估计的鲁棒性通过MNL运动回归提高。
translated by 谷歌翻译
视频通常将流和连续的视觉数据记录为离散的连续帧。由于存储成本对于高保真度的视频来说是昂贵的,因此大多数存储以相对较低的分辨率和帧速率存储。最新的时空视频超分辨率(STVSR)的工作是开发出来的,以将时间插值和空间超分辨率纳入统一框架。但是,其中大多数仅支持固定的上采样量表,这限制了其灵活性和应用。在这项工作中,我们没有遵循离散表示,我们提出了视频隐式神经表示(videoinr),并显示了其对STVSR的应用。学到的隐式神经表示可以解码为任意空间分辨率和帧速率的视频。我们表明,Videoinr在常见的上采样量表上使用最先进的STVSR方法实现了竞争性能,并且在连续和训练的分布量表上显着优于先前的作品。我们的项目页面位于http://zeyuan-chen.com/videoinr/。
translated by 谷歌翻译
可以通过定期预测未来的框架以增强虚拟现实应用程序中的用户体验,从而解决了低计算设备上图形渲染高帧速率视频的挑战。这是通过时间视图合成(TVS)的问题来研究的,该问题的目标是预测给定上一个帧的视频的下一个帧以及上一个和下一个帧的头部姿势。在这项工作中,我们考虑了用户和对象正在移动的动态场景的电视。我们设计了一个将运动解散到用户和对象运动中的框架,以在预测下一帧的同时有效地使用可用的用户运动。我们通过隔离和估计过去框架的3D对象运动,然后推断它来预测对象的运动。我们使用多平面图像(MPI)作为场景的3D表示,并将对象运动作为MPI表示中相应点之间的3D位移建模。为了在估计运动时处理MPI中的稀疏性,我们将部分卷积和掩盖的相关层纳入了相应的点。然后将预测的对象运动与给定的用户或相机运动集成在一起,以生成下一帧。使用不合格的填充模块,我们合成由于相机和对象运动而发现的区域。我们为动态场景的电视开发了一个新的合成数据集,该数据集由800个以全高清分辨率组成的视频组成。我们通过数据集和MPI Sintel数据集上的实验表明我们的模型优于文献中的所有竞争方法。
translated by 谷歌翻译