最近的作品表明,隐式神经表示(INR)具有信号导数的有意义表示的能力。在这项工作中,我们利用该属性来执行视频框架插值(VFI),通过明确限制INR的衍生物以满足光流约束方程。我们仅使用目标视频及其光流,在有限的运动范围内实现了最先进的VFI,而无需从其他培训数据中学习插值操作员。我们进一步表明,限制INR衍生物不仅可以更好地插值中间框架,还可以提高狭窄网络适合观察到的帧的能力,这暗示了潜在的视频压缩和INR优化的应用。
translated by 谷歌翻译
隐式神经表示(INR)被出现为代表信号的强大范例,例如图像,视频,3D形状等。尽管它已经示出了能够表示精细细节的能力,但其效率尚未得到广泛研究数据表示。在INR中,数据以神经网络的参数的形式存储,并且通用优化算法通常不会利用信号中的空间和时间冗余。在本文中,我们建议通过明确地删除数据冗余来表示和压缩视频的新型INR方法。我们提出了跨视频帧和残差的主体剩余流场(NRFF)而不是存储原始RGB颜色,而不是存储原始RGB颜色。维护通常更光滑和更复杂的运动信息,比原始信号更少,需要更少的参数。此外,重用冗余像素值进一步提高了网络参数效率。实验结果表明,所提出的方法优于基线方法的显着边际。代码可用于https://github.com/daniel03c1/eff_video_repruseentation。
translated by 谷歌翻译
视频帧插值,旨在在视频序列中合成不存在中间帧,是计算机视觉中的重要研究主题。现有的视频帧插值方法在特定假设下实现了显着的结果,例如瞬间或已知的曝光时间。然而,在复杂的真实情况下,视频的时间前锋,即每秒帧(FPS)和帧曝光时间,可能与不同的相机传感器不同。当在从训练中的不同曝光设置下进行测试视频时,内插帧将遭受显着的错位问题。在这项工作中,我们在一般情况下解决了视频帧插值问题,其中可以在不确定的曝光(和间隔)时间下获取输入帧。与以前可以应用于特定时间的方法的方法不同,我们从四个连续的尖锐帧或两个连续的模糊帧中导出一般的曲线运动轨迹公式,没有时间前导者。此外,利用相邻运动轨迹内的约束,我们设计了一种新的光学流细化策略,以获得更好的插值结果。最后,实验表明,一个训练有素的模型足以在复杂的真实情况下合成高质量的慢动作视频。代码可在https://github.com/yjzhang96/uti-vfi上使用。
translated by 谷歌翻译
The quantitative evaluation of optical flow algorithms by Barron et al. (1994) led to significant advances in performance. The challenges for optical flow algorithms today go beyond the datasets and evaluation methods proposed in that paper. Instead, they center on problems associated with complex natural scenes, including nonrigid motion, real sensor noise, and motion discontinuities. We propose a new set of benchmarks and evaluation methods for the next generation of optical flow algorithms. To that end, we contribute four types of data to test different aspects of optical flow algorithms: (1) sequences with nonrigid motion where the ground-truth flow is determined by A preliminary version of this paper appeared in the IEEE International Conference on Computer Vision (Baker et al. 2007).
translated by 谷歌翻译
我们提出了一种压缩具有隐式神经表示的全分辨率视频序列的方法。每个帧表示为映射坐标位置到像素值的神经网络。我们使用单独的隐式网络来调制坐标输入,从而实现帧之间的有效运动补偿。与一个小的残余网络一起,这允许我们有效地相对于前一帧压缩p帧。通过使用学习的整数量化存储网络权重,我们进一步降低了比特率。我们呼叫隐式像素流(IPF)的方法,提供了几种超简化的既定神经视频编解码器:它不需要接收器可以访问预先磨普的神经网络,不使用昂贵的内插基翘曲操作,而不是需要单独的培训数据集。我们展示了神经隐式压缩对图像和视频数据的可行性。
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
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
在本文中,我们提出了一种算法,以在动态场景的两对图像之间插值。尽管在过去的几年中,在框架插值方面取得了重大进展,但当前的方法无法处理具有亮度和照明变化的图像,即使很快将图像捕获也很常见。我们建议通过利用现有的光流方法来解决这个问题,这些方法对照明的变化非常健壮。具体而言,使用使用现有预训练的流动网络估算的双向流,我们预测了从中间帧到两个输入图像的流。为此,我们建议将双向流编码为由超网络提供动力的基于坐标的网络,以获得跨时间的连续表示流。一旦获得了估计的流,我们就会在现有的混合网络中使用它们来获得最终的中间帧。通过广泛的实验,我们证明我们的方法能够比最新的框架插值算法产生明显更好的结果。
translated by 谷歌翻译
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
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
Many video enhancement algorithms rely on optical flow to register frames in a video sequence. Precise flow estimation is however intractable; and optical flow itself is often a sub-optimal representation for particular video processing tasks. In this paper, we propose task-oriented flow (TOFlow), a motion representation learned in a selfsupervised, task-specific manner. We design a neural network with a trainable motion estimation component and a video processing component, and train them jointly to learn the task-oriented flow. For evaluation, we build Vimeo-90K, a large-scale, high-quality video dataset for low-level video processing. TOFlow outperforms traditional optical flow on standard benchmarks as well as our Vimeo-90K dataset in three video processing tasks: frame interpolation, video denoising/deblocking, and video super-resolution. IntroductionMotion estimation is a key component in video processing tasks such as temporal frame interpolation, video denoising,
translated by 谷歌翻译
视频框架插值(VFI)实现了许多可能涉及时间域的重要应用程序,例如慢运动播放或空间域,例如停止运动序列。我们专注于以前的任务,其中关键挑战之一是在存在复杂运动的情况下处理高动态范围(HDR)场景。为此,我们探索了双曝光传感器的可能优势,这些传感器很容易提供尖锐的短而模糊的长曝光,这些曝光是空间注册并在时间上对齐的两端。这样,运动模糊会在场景运动上暂时连续的信息,这些信息与尖锐的参考结合在一起,可以在单个相机拍摄中进行更精确的运动采样。我们证明,这促进了VFI任务中更复杂的运动重建以及HDR框架重建,迄今为止仅考虑到最初被捕获的框架,而不是插值之间的框架。我们设计了一个在这些任务中训练的神经网络,这些神经网络明显优于现有解决方案。我们还提出了一个场景运动复杂性的度量,该指标在测试时间提供了对VFI方法的性能的重要见解。
translated by 谷歌翻译
视频预测是一个推断任务,可以预测给定过去帧的未来帧,而视频框架插值是一个插值任务,可以估算两个帧之间的中间帧。我们目睹了视频框架插值的巨大进步,但野外的一般视频预测仍然是一个悬而未决的问题。受视频框架插值的照片真实结果的启发,我们为视频框架插值提供了一个新的优化框架,用于视频预测,其中我们根据插值模型解决了推断问题。我们的视频预测框架是基于优化的,而无需训练数据集,而无需培训数据集,因此训练数据和测试数据之间没有域间隙问题。另外,我们的方法不需要任何其他信息,例如语义或实例地图,这使我们的框架适用于任何视频。关于CityScapes,Kitti,Davis,Middlebury和Vimeo90K数据集的广泛实验表明,在一般情况下,我们的视频预测结果非常强大,我们的方法优于其他需要大量培训数据或额外语义信息的视频预测方法。
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
传统摄像机测量图像强度。相比之下,事件相机以异步测量每像素的时间强度变化。恢复事件的强度是一个流行的研究主题,因为重建的图像继承了高动态范围(HDR)和事件的高速属性;因此,它们可以在许多机器人视觉应用中使用并生成慢动作HDR视频。然而,最先进的方法通过训练映射到图像经常性神经网络(RNN)来解决这个问题,这缺乏可解释性并且难以调整。在这项工作中,我们首次展示运动和强度估计的联合问题导致我们以模拟基于事件的图像重建作为可以解决的线性逆问题,而无需训练图像重建RNN。相反,基于古典和学习的图像前导者可以用于解决问题并从重建的图像中删除伪影。实验表明,尽管仅使用来自短时间间隔(即,没有复发连接),但是,尽管只使用来自短时间间隔的数据,所提出的方法会产生视觉质量的图像。我们的方法还可用于提高首先估计图像Laplacian的方法重建的图像的质量;在这里,我们的方法可以被解释为由图像前提引导的泊松重建。
translated by 谷歌翻译
The FlowNet demonstrated that optical flow estimation can be cast as a learning problem. However, the state of the art with regard to the quality of the flow has still been defined by traditional methods. Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods. In this paper, we advance the concept of end-to-end learning of optical flow and make it work really well. The large improvements in quality and speed are caused by three major contributions: first, we focus on the training data and show that the schedule of presenting data during training is very important. Second, we develop a stacked architecture that includes warping of the second image with intermediate optical flow. Third, we elaborate on small displacements by introducing a subnetwork specializing on small motions. FlowNet 2.0 is only marginally slower than the original FlowNet but decreases the estimation error by more than 50%. It performs on par with state-of-the-art methods, while running at interactive frame rates. Moreover, we present faster variants that allow optical flow computation at up to 140fps with accuracy matching the original FlowNet.
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
Videos shot by laymen using hand-held cameras contain undesirable shaky motion. Estimating the global motion between successive frames, in a manner not influenced by moving objects, is central to many video stabilization techniques, but poses significant challenges. A large body of work uses 2D affine transformations or homography for the global motion. However, in this work, we introduce a more general representation scheme, which adapts any existing optical flow network to ignore the moving objects and obtain a spatially smooth approximation of the global motion between video frames. We achieve this by a knowledge distillation approach, where we first introduce a low pass filter module into the optical flow network to constrain the predicted optical flow to be spatially smooth. This becomes our student network, named as \textsc{GlobalFlowNet}. Then, using the original optical flow network as the teacher network, we train the student network using a robust loss function. Given a trained \textsc{GlobalFlowNet}, we stabilize videos using a two stage process. In the first stage, we correct the instability in affine parameters using a quadratic programming approach constrained by a user-specified cropping limit to control loss of field of view. In the second stage, we stabilize the video further by smoothing global motion parameters, expressed using a small number of discrete cosine transform coefficients. In extensive experiments on a variety of different videos, our technique outperforms state of the art techniques in terms of subjective quality and different quantitative measures of video stability. The source code is publicly available at \href{https://github.com/GlobalFlowNet/GlobalFlowNet}{https://github.com/GlobalFlowNet/GlobalFlowNet}
translated by 谷歌翻译
滚动快门(RS)失真可以解释为在RS摄像机曝光期间,随着时间的推移从瞬时全局快门(GS)框架中挑选一排像素。这意味着每个即时GS帧的信息部分,依次是嵌入到行依赖性失真中。受到这一事实的启发,我们解决了扭转这一过程的挑战性任务,即从rs失真中的图像中提取未变形的GS框架。但是,由于RS失真与其他因素相结合,例如读数设置以及场景元素与相机的相对速度,因此仅利用临时相邻图像之间的几何相关性的型号,在处理数据中,具有不同的读数设置和动态场景的数据中遭受了不良的通用性。带有相机运动和物体运动。在本文中,我们建议使用双重RS摄像机捕获的一对图像,而不是连续的框架,而RS摄像机则具有相反的RS方向,以完成这项极具挑战性的任务。基于双重反转失真的对称和互补性,我们开发了一种新型的端到端模型,即IFED,以通过卢比时间对速度场的迭代学习来生成双重光流序列。广泛的实验结果表明,IFED优于天真的级联方案,以及利用相邻RS图像的最新艺术品。最重要的是,尽管它在合成数据集上进行了训练,但显示出在从现实世界中的RS扭曲的动态场景图像中检索GS框架序列有效。代码可在https://github.com/zzh-tech/dual-versed-rs上找到。
translated by 谷歌翻译
A difficult example for video frame interpolation. Our approach produces a high-quality result in spite of the delicate flamingo leg that is subject to large motion. This is a video figure that is best viewed using Adobe Reader.
translated by 谷歌翻译