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.

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).

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.

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.

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.

传统上，本征成像或内在图像分解被描述为将图像分解为两层：反射率，材料的反射率;和一个阴影，由光和几何之间的相互作用产生。近年来，深入学习技术已广泛应用，以提高这些分离的准确性。在本调查中，我们概述了那些在知名内在图像数据集和文献中使用的相关度量的结果，讨论了预测所需的内在图像分解的适用性。虽然Lambertian的假设仍然是许多方法的基础，但我们表明，对图像形成过程更复杂的物理原理组件的潜力越来越意识到，这是光学准确的材料模型和几何形状，更完整的逆轻型运输估计。考虑使用的前瞻和模型以及驾驶分解过程的学习架构和方法，我们将这些方法分类为分解的类型。考虑到最近神经，逆和可微分的渲染技术的进步，我们还提供了关于未来研究方向的见解。

全向视频中的光流估计面临两个重要问题：缺乏基准数据集以及调整基于视频的方法以适应全向性质的挑战。本文提出了第一个具有360度视野Flow360的感知上天然合成的全向基准数据集，其中有40个不同的视频和4,000个视频帧。我们在数据集和现有的光流数据集之间进行了全面的特征分析和比较，这些数据集表现出感知现实主义，独特性和多样性。为了适应全向性质，我们提出了一个新颖的暹罗表示学习框架（SLOF）。我们以对比度的方式训练我们的网络，并结合了对比度损失和光流损失的混合损失函数。广泛的实验验证了所提出的框架的有效性，并在最新方法中显示出40％的性能提高。我们的Flow360数据集和代码可在https://siamlof.github.io/上找到。

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

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.

Estimating human pose, shape, and motion from images and videos are fundamental challenges with many applications. Recent advances in 2D human pose estimation use large amounts of manually-labeled training data for learning convolutional neural networks (CNNs). Such data is time consuming to acquire and difficult to extend. Moreover, manual labeling of 3D pose, depth and motion is impractical. In this work we present SURREAL (Synthetic hUmans foR REAL tasks): a new large-scale dataset with synthetically-generated but realistic images of people rendered from 3D sequences of human motion capture data. We generate more than 6 million frames together with ground truth pose, depth maps, and segmentation masks. We show that CNNs trained on our synthetic dataset allow for accurate human depth estimation and human part segmentation in real RGB images. Our results and the new dataset open up new possibilities for advancing person analysis using cheap and large-scale synthetic data.

We learn to compute optical flow by combining a classical spatial-pyramid formulation with deep learning. This estimates large motions in a coarse-to-fine approach by warping one image of a pair at each pyramid level by the current flow estimate and computing an update to the flow. Instead of the standard minimization of an objective function at each pyramid level, we train one deep network per level to compute the flow update. Unlike the recent FlowNet approach, the networks do not need to deal with large motions; these are dealt with by the pyramid. This has several advantages. First, our Spatial Pyramid Network (SPyNet) is much simpler and 96% smaller than FlowNet in terms of model parameters. This makes it more efficient and appropriate for embedded applications. Second, since the flow at each pyramid level is small (< 1 pixel), a convolutional approach applied to pairs of warped images is appropriate. Third, unlike FlowNet, the learned convolution filters appear similar to classical spatio-temporal filters, giving insight into the method and how to improve it. Our results are more accurate than FlowNet on most standard benchmarks, suggesting a new direction of combining classical flow methods with deep learning.1 This, of course, has well-known limitations, which we discuss later.

近年来，Imbersive显示器（例如VR耳机，AR眼镜，多视图显示器，自由点电视）已成为一种新的展示技术，与传统显示相比，提供了更好的视觉体验和观众的参与度。随着3D视频和展示技术的发展，高动态范围（HDR）摄像机和显示器的消费市场迅速增长。缺乏适当的实验数据是3D HDR视频技术领域的主要研究工作的关键障碍。同样，足够的现实世界多曝光实验数据集的不可用是用于HDR成像研究的主要瓶颈，从而限制了观众的体验质量（QOE）。在本文中，我们介绍了在印度理工学院马德拉斯校园内捕获的多元化立体曝光数据集，该数据集是多元化的动植物的所在地。该数据集使用ZED立体相机捕获，并提供户外位置的复杂场景，例如花园，路边景观，节日场地，建筑物和室内地区，例如学术和居住区。提出的数据集可容纳宽深度范围，复杂的深度结构，使物体运动复杂化，照明变化，丰富的色彩动态，纹理差异，除了通过移动摄像机和背景运动引入的显着随机性。拟议的数据集可公开向研究界公开使用。此外，详细描述了捕获，对齐和校准多曝光立体视频和图像的过程。最后，我们讨论了有关HDR成像，深度估计，一致的音调映射和3D HDR编码的进度，挑战，潜在用例和未来研究机会。

Stereo matching is one of the most active research areas in computer vision. While a large number of algorithms for stereo correspondence have been developed, relatively little work has been done on characterizing their performance. In this paper, we present a taxonomy of dense, two-frame stereo methods. Our taxonomy is designed to assess the different components and design decisions made in individual stereo algorithms. Using this taxonomy, we compare existing stereo methods and present experiments evaluating the performance of many different variants. In order to establish a common software platform and a collection of data sets for easy evaluation, we have designed a stand-alone, flexible C++ implementation that enables the evaluation of individual components and that can easily be extended to include new algorithms. We have also produced several new multi-frame stereo data sets with ground truth and are making both the code and data sets available on the Web. Finally, we include a comparative evaluation of a large set of today's best-performing stereo algorithms.

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.

Visual object analysis researchers are increasingly experimenting with video, because it is expected that motion cues should help with detection, recognition, and other analysis tasks. This paper presents the Cambridge-driving Labeled Video Database (CamVid) as the first collection of videos with object class semantic labels, complete with metadata. The database provides ground truth labels that associate each pixel with one of 32 semantic classes. The database addresses the need for experimental data to quantitatively evaluate emerging algorithms. While most videos are filmed with fixed-position CCTV-style cameras, our data was captured from the perspective of a driving automobile. The driving scenario increases the number and heterogeneity of the observed object classes. Over 10 min of high quality 30 Hz footage is being provided, with corresponding semantically labeled images at 1 Hz and in part, 15 Hz. The CamVid Database offers four contributions that are relevant to object analysis researchers. First, the per-pixel semantic segmentation of over 700 images was specified manually, and was then inspected and confirmed by a second person for accuracy. Second, the high-quality and large resolution color video images in the database represent valuable extended duration digitized footage to those interested in driving scenarios or ego-motion. Third, we filmed calibration sequences for the camera color response and intrinsics, and computed a 3D camera pose for each frame in the sequences. Finally, in support of expanding this or other databases, we present custom-made labeling software for assisting users who wish to paint precise class-labels for other images and videos. We evaluate the relevance of the database by measuring the performance of an algorithm from each of three distinct domains: multi-class object recognition, pedestrian detection, and label propagation.

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。

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。

Today, visual recognition systems are still rarely employed in robotics applications. Perhaps one of the main reasons for this is the lack of demanding benchmarks that mimic such scenarios. In this paper, we take advantage of our autonomous driving platform to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry / SLAM and 3D object detection. Our recording platform is equipped with four high resolution video cameras, a Velodyne laser scanner and a state-of-the-art localization system. Our benchmarks comprise 389 stereo and optical flow image pairs, stereo visual odometry sequences of 39.2 km length, and more than 200k 3D object annotations captured in cluttered scenarios (up to 15 cars and 30 pedestrians are visible per image). Results from state-of-the-art algorithms reveal that methods ranking high on established datasets such as Middlebury perform below average when being moved outside the laboratory to the real world. Our goal is to reduce this bias by providing challenging benchmarks with novel difficulties to the computer vision community. Our benchmarks are available online at: www.cvlibs.net/datasets/kitti

This paper proposes a novel model and dataset for 3D scene flow estimation with an application to autonomous driving. Taking advantage of the fact that outdoor scenes often decompose into a small number of independently moving objects, we represent each element in the scene by its rigid motion parameters and each superpixel by a 3D plane as well as an index to the corresponding object. This minimal representation increases robustness and leads to a discrete-continuous CRF where the data term decomposes into pairwise potentials between superpixels and objects. Moreover, our model intrinsically segments the scene into its constituting dynamic components. We demonstrate the performance of our model on existing benchmarks as well as a novel realistic dataset with scene flow ground truth. We obtain this dataset by annotating 400 dynamic scenes from the KITTI raw data collection using detailed 3D CAD models for all vehicles in motion. Our experiments also reveal novel challenges which cannot be handled by existing methods.

与无监督培训相比，对光流预测因子的监督培训通常会产生更好的准确性。但是，改进的性能通常以较高的注释成本。半监督的培训与注释成本相比，准确性的准确性。我们使用一种简单而有效的半监督训练方法来表明，即使一小部分标签也可以通过无监督的训练来提高流量准确性。此外，我们提出了基于简单启发式方法的主动学习方法，以进一步减少实现相同目标准确性所需的标签数量。我们对合成和真实光流数据集的实验表明，我们的半监督网络通常需要大约50％的标签才能达到接近全标签的精度，而在Sintel上有效学习只有20％左右。我们还分析并展示了有关可能影响主动学习绩效的因素的见解。代码可在https://github.com/duke-vision/optical-flow-active-learning-release上找到。