Existing correspondence datasets for two-dimensional (2D) cartoon suffer from simple frame composition and monotonic movements, making them insufficient to simulate real animations. In this work, we present a new 2D animation visual correspondence dataset, AnimeRun, by converting open source three-dimensional (3D) movies to full scenes in 2D style, including simultaneous moving background and interactions of multiple subjects. Our analyses show that the proposed dataset not only resembles real anime more in image composition, but also possesses richer and more complex motion patterns compared to existing datasets. With this dataset, we establish a comprehensive benchmark by evaluating several existing optical flow and segment matching methods, and analyze shortcomings of these methods on animation data. Data, code and other supplementary materials are available at https://lisiyao21.github.io/projects/AnimeRun.

Ground truth optical flow is difficult to measure in real scenes with natural motion. As a result, optical flow data sets are restricted in terms of size, complexity, and diversity, making optical flow algorithms difficult to train and test on realistic data. We introduce a new optical flow data set derived from the open source 3D animated short film Sintel. This data set has important features not present in the popular Middlebury flow evaluation: long sequences, large motions, specular reflections, motion blur, defocus blur, and atmospheric effects. Because the graphics data that generated the movie is open source, we are able to render scenes under conditions of varying complexity to evaluate where existing flow algorithms fail. We evaluate several recent optical flow algorithms and find that current highly-ranked methods on the Middlebury evaluation have difficulty with this more complex data set suggesting further research on optical flow estimation is needed. To validate the use of synthetic data, we compare the image-and flow-statistics of Sintel to those of real films and videos and show that they are similar. The data set, metrics, and evaluation website are publicly available.

Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated dataset. The present paper extends the concept of optical flow estimation via convolutional networks to disparity and scene flow estimation. To this end, we propose three synthetic stereo video datasets with sufficient realism, variation, and size to successfully train large networks. Our datasets are the first large-scale datasets to enable training and evaluating scene flow methods. Besides the datasets, we present a convolutional network for real-time disparity estimation that provides state-of-the-art results. By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.

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).

从视频中获得地面真相标签很具有挑战性，因为在像素流标签的手动注释非常昂贵且费力。此外，现有的方法试图将合成数据集的训练模型调整到真实的视频中，该视频不可避免地遭受了域差异并阻碍了现实世界应用程序的性能。为了解决这些问题，我们提出了RealFlow，这是一个基于期望最大化的框架，可以直接从任何未标记的现实视频中创建大规模的光流数据集。具体而言，我们首先估计一对视频帧之间的光流，然后根据预测流从该对中合成新图像。因此，新图像对及其相应的流可以被视为新的训练集。此外，我们设计了一种逼真的图像对渲染（RIPR）模块，该模块采用软磁性裂口和双向孔填充技术来减轻图像合成的伪像。在E-Step中，RIPR呈现新图像以创建大量培训数据。在M-Step中，我们利用生成的训练数据来训练光流网络，该数据可用于估计下一个E步骤中的光流。在迭代学习步骤中，流网络的能力逐渐提高，流量的准确性以及合成数据集的质量也是如此。实验结果表明，REALFLOW的表现优于先前的数据集生成方法。此外，基于生成的数据集，我们的方法与受监督和无监督的光流方法相比，在两个标准基准测试方面达到了最先进的性能。我们的代码和数据集可从https://github.com/megvii-research/realflow获得

半监控视频对象分段（VOS）旨在在视频序列中分段一些移动对象，其中通过注释第一帧来指定这些对象。已经考虑了许多现有的半监督VOS方法以提高分割精度的光学流程。然而，由于光学流量估计的高复杂性，光流基的半监控VOS方法不能实时运行。在该研究中提出了由特征提取网络（F），外观网络（A），运动网络（A）和集成网络（I）组成的FAMINET，以解决上述问题。外观网络基于对象的静态外观输出初始分割结果。运动网络通过很少的参数估计光学流量，这些参数通过在线记忆算法快速优化，该算法被称为松弛最陡血迹。集成网络使用光流来改进初始分割结果。广泛的实验表明，FAMINET在DAVIS和YOUTUBE-VOS基准上表现出其他最先进的半监督VOS方法，并且它在准确性和效率之间实现了良好的权衡。我们的代码可在https://github.com/liuziyang123/faminet获得。

无监督的对光流计算的深度学习取得了令人鼓舞的结果。大多数现有的基于深网的方法都依赖图像亮度一致性和局部平滑度约束来训练网络。他们的性能在发生重复纹理或遮挡的区域降低。在本文中，我们提出了深层的外两极流，这是一种无监督的光流方法，将全局几何约束结合到网络学习中。特别是，我们研究了多种方式在流量估计中强制执行外两极约束。为了减轻在可能存在多个动作的动态场景中遇到的“鸡肉和蛋”类型的问题，我们提出了一个低级别的约束以及对培训的订婚结合的约束。各种基准测试数据集的实验结果表明，与监督方法相比，我们的方法实现了竞争性能，并且优于最先进的无监督深度学习方法。

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.

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,

Convolutional neural networks (CNNs) have recently been very successful in a variety of computer vision tasks, especially on those linked to recognition. Optical flow estimation has not been among the tasks where CNNs were successful. In this paper we construct appropriate CNNs which are capable of solving the optical flow estimation problem as a supervised learning task. We propose and compare two architectures: a generic architecture and another one including a layer that correlates feature vectors at different image locations.Since existing ground truth datasets are not sufficiently large to train a CNN, we generate a synthetic Flying Chairs dataset. We show that networks trained on this unrealistic data still generalize very well to existing datasets such as Sintel and KITTI, achieving competitive accuracy at frame rates of 5 to 10 fps.

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.

基于深度学习的当前计算机视觉任务需要大量数据，并具有用于模型培训或测试的注释，尤其是在某些密集的估计任务中，例如光流分段和深度估计。实际上，密集估计任务的手动标记非常困难甚至不可能，并且数据集的场景通常仅限于较小的范围，这极大地限制了社区的发展。为了克服这种缺陷，我们提出了一种合成数据集生成方法，以获取无繁重的手动劳动力的可扩展数据集。通过这种方法，我们构建了一个名为Minenavi的数据集，该数据集包含来自飞机的第一镜头视频视频素材，并与准确的地面真相相匹配，以实现飞机导航应用中的深度估算。我们还提供定量实验，以证明通过Minenavi数据集进行预训练可以提高深度估计模型的性能，并加快模型在真实场景数据上的收敛性。由于合成数据集在深层模型的训练过程中与现实世界数据集具有相似的效果，因此我们还提供了具有单眼深度估计方法的其他实验，以证明各种因素在我们的数据集中的影响，例如照明条件和运动模式。

Image dehazing is one of the important and popular topics in computer vision and machine learning. A reliable real-time dehazing method with reliable performance is highly desired for many applications such as autonomous driving, security surveillance, etc. While recent learning-based methods require datasets containing pairs of hazy images and clean ground truth, it is impossible to capture them in real scenes. Many existing works compromise this difficulty to generate hazy images by rendering the haze from depth on common RGBD datasets using the haze imaging model. However, there is still a gap between the synthetic datasets and real hazy images as large datasets with high-quality depth are mostly indoor and depth maps for outdoor are imprecise. In this paper, we complement the existing datasets with a new, large, and diverse dehazing dataset containing real outdoor scenes from High-Definition (HD) 3D movies. We select a large number of high-quality frames of real outdoor scenes and render haze on them using depth from stereo. Our dataset is clearly more realistic and more diversified with better visual quality than existing ones. More importantly, we demonstrate that using this dataset greatly improves the dehazing performance on real scenes. In addition to the dataset, we also evaluate a series state of the art methods on the proposed benchmarking datasets.

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。

在本文中，我们提出了USEGSCENE，该框架用于使用卷积神经网络对立体声相机图像的深度，光流和自我感动的无监督学习。我们的框架利用语义信息来改善深度和光流图的正则化，多模式融合和遮挡填充考虑动态刚性对象运动作为独立的SE（3）转换。此外，我们与纯照相匹配匹配互补，我们提出了连续图像之间语义特征，像素类别和对象实例边界的匹配。与以前的方法相反，我们提出了一个网络体系结构，该网络体系结构可以使用共享编码器共同预测所有输出，并允许在任务域上传递信息，例如，光流的预测可以从深度的预测中受益。此外，我们明确地了解网络内部的深度和光流遮挡图，这些图被利用，以改善这些区域的预测。我们在流行的Kitti数据集上介绍了结果，并表明我们的方法以大幅度的优于其他方法。

本文的目的是一个模型，能够在视频中发现，跟踪和细分多个移动对象。我们做出四个贡献：首先，我们引入了一个以对象为中心的分段模型，具有深度订购的层表示。这是使用摄入光流的变压器体系结构的变体来实现的，每个查询向量为整个视频指定对象及其层。该模型可以有效地发现多个移动对象并处理相互阻塞。其次，我们引入了一条可扩展的管道，用于生成具有多个对象的合成训练数据，从而大大降低了对劳动密集型注释的要求，并支持SIM2REAL概括；第三，我们表明该模型能够学习对象的持久性和时间形状的一致性，并能够预测Amodal分割掩码。第四，我们评估了标准视频细分基准测试模型，戴维斯，MOCA，SEGTRACK，FBMS-59，并实现最新的无监督分割性能，甚至优于几种监督方法。通过测试时间适应，我们观察到进一步的性能提高。

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。

快速移动受试者的运动模糊是摄影中的一个长期问题，由于收集效率有限，尤其是在弱光条件下，在手机上非常常见。尽管近年来我们目睹了图像脱毛的巨大进展，但大多数方法都需要显着的计算能力，并且在处理高分辨率照片的情况下具有严重的局部动作。为此，我们根据手机的双摄像头融合技术开发了一种新颖的面部脱毛系统。该系统检测到主题运动以动态启用参考摄像头，例如，最近在高级手机上通常可用的Ultrawide Angle摄像机，并捕获带有更快快门设置的辅助照片。虽然主镜头是低噪音但模糊的，但参考镜头却很锋利，但嘈杂。我们学习ML模型，以对齐和融合这两张镜头，并在没有运动模糊的情况下输出清晰的照片。我们的算法在Google Pixel 6上有效运行，每次拍摄需要463毫秒的开销。我们的实验证明了系统对替代单片，多帧，面部特异性和视频脱张算法以及商业产品的优势和鲁棒性。据我们所知，我们的工作是第一个用于面部运动脱毛的移动解决方案，在各种运动和照明条件下，在数千个图像中可靠地工作。

我们研究了从单个运动毛发图像中恢复详细运动的挑战性问题。该问题的现有解决方案估算一个单个图像序列，而无需考虑每个区域的运动歧义。因此，结果倾向于收敛到多模式可能性的平均值。在本文中，我们明确说明了这种运动歧义，使我们能够详细地生成多个合理的解决方案。关键思想是引入运动引导表示，这是对仅有四个离散运动方向的2D光流的紧凑量量化。在运动引导的条件下，模糊分解通过使用新型的两阶段分解网络导致了特定的，明确的解决方案。我们提出了一个模糊分解的统一框架，该框架支持各种界面来生成我们的运动指导，包括人类输入，来自相邻视频帧的运动信息以及从视频数据集中学习。关于合成数据集和现实世界数据的广泛实验表明，所提出的框架在定性和定量上优于以前的方法，并且还具有生产物理上合理和多样的解决方案的优点。代码可从https://github.com/zzh-tech/animation-from-blur获得。