近期对抗性生成建模的突破导致了能够生产高质量的视频样本的模型,即使在真实世界视频的大型和复杂的数据集上也是如此。在这项工作中,我们专注于视频预测的任务,其中给出了从视频中提取的一系列帧,目标是生成合理的未来序列。我们首先通过对鉴别器分解进行系统的实证研究并提出产生更快的收敛性和更高性能的系统来提高本领域的最新技术。然后,我们分析发电机中的复发单元,并提出了一种新的复发单元,其根据预测的运动样本来改变其过去的隐藏状态,并改进它以处理DIS闭塞,场景变化和其他复杂行为。我们表明,这种经常性单位始终如一地优于以前的设计。我们的最终模型导致最先进的性能中的飞跃,从大型动力学-600数据集中获得25.7的测试集Frechet视频距离为25.7,下降到69.2。
translated by 谷歌翻译
A core challenge for an agent learning to interact with the world is to predict how its actions affect objects in its environment. Many existing methods for learning the dynamics of physical interactions require labeled object information. However, to scale real-world interaction learning to a variety of scenes and objects, acquiring labeled data becomes increasingly impractical. To learn about physical object motion without labels, we develop an action-conditioned video prediction model that explicitly models pixel motion, by predicting a distribution over pixel motion from previous frames. Because our model explicitly predicts motion, it is partially invariant to object appearance, enabling it to generalize to previously unseen objects. To explore video prediction for real-world interactive agents, we also introduce a dataset of 59,000 robot interactions involving pushing motions, including a test set with novel objects. In this dataset, accurate prediction of videos conditioned on the robot's future actions amounts to learning a "visual imagination" of different futures based on different courses of action. Our experiments show that our proposed method produces more accurate video predictions both quantitatively and qualitatively, when compared to prior methods.
translated by 谷歌翻译
视觉世界可以以稀疏相互作用的不同实体来嘲笑。在动态视觉场景中发现这种组合结构已被证明对端到端的计算机视觉方法有挑战,除非提供明确的实例级别的监督。利用运动提示的基于老虎机的模型最近在学习代表,细分和跟踪对象的情况下没有直接监督显示了巨大的希望,但是它们仍然无法扩展到复杂的现实世界多对象视频。为了弥合这一差距,我们从人类发展中汲取灵感,并假设以深度信号形式的场景几何形状的信息可以促进以对象为中心的学习。我们介绍了一种以对象为中心的视频模型SAVI ++,该模型经过训练,可以预测基于插槽的视频表示的深度信号。通过进一步利用模型缩放的最佳实践,我们能够训练SAVI ++以细分使用移动摄像机记录的复杂动态场景,其中包含在自然主义背景上具有不同外观的静态和移动对象,而无需进行分割监督。最后,我们证明,通过使用从LIDAR获得的稀疏深度信号,Savi ++能够从真实World Waymo Open DataSet中的视频中学习新兴对象细分和跟踪。
translated by 谷歌翻译
我们提出了一个视频生成模型,该模型可以准确地重现对象运动,摄像头视图的变化以及随着时间的推移而产生的新内容。现有的视频生成方法通常无法生成新内容作为时间的函数,同时保持在真实环境中预期的一致性,例如合理的动态和对象持久性。一个常见的故障情况是,由于过度依赖归纳偏见而提供时间一致性,因此内容永远不会改变,例如单个潜在代码决定整个视频的内容。在另一个极端情况下,没有长期一致性,生成的视频可能会在不同场景之间不切实际。为了解决这些限制,我们通过重新设计暂时的潜在表示并通过较长的视频培训从数据中学习长期一致性来优先考虑时间轴。为此,我们利用了两阶段的培训策略,在该策略中,我们以低分辨率和高分辨率的较短视频分别训练了较长的视频。为了评估模型的功能,我们介绍了两个新的基准数据集,并明确关注长期时间动态。
translated by 谷歌翻译
视频显示连续事件,但大多数 - 如果不是全部 - 视频综合框架及时酌情对待它们。在这项工作中,我们想到它们应该是连续的信号的视频,并扩展神经表示的范式以构建连续时间视频发生器。为此,我们首先通过位置嵌入的镜头设计连续运动表示。然后,我们探讨了在非常稀疏的视频上培训问题,并证明可以使用每剪辑的少数为2帧来学习良好的发电机。之后,我们重新思考传统的图像和视频鉴别器对并建议使用基于Hypernetwork的一个。这降低了培训成本并向发电机提供了更丰富的学习信号,使得可以首次直接培训1024美元$ ^ 2 $视频。我们在Stylegan2的顶部构建我们的模型,并且在同样的分辨率下培训速度速度较高5%,同时实现几乎相同的图像质量。此外,我们的潜在空间具有类似的属性,使我们的方法可以及时传播的空间操纵。我们可以在任意高帧速率下任意长的视频,而现有工作努力以固定速率生成均匀的64个帧。我们的模型在四个现代256美元$ ^ 2 $视频综合基准测试中实现最先进的结果,一个1024美元$ ^ 2 $ state。视频和源代码在项目网站上提供:https://universome.github.io/stylegan-v。
translated by 谷歌翻译
不确定性在未来预测中起关键作用。未来是不确定的。这意味着可能有很多可能的未来。未来的预测方法应涵盖坚固的全部可能性。在自动驾驶中,涵盖预测部分中的多种模式对于做出安全至关重要的决策至关重要。尽管近年来计算机视觉系统已大大提高,但如今的未来预测仍然很困难。几个示例是未来的不确定性,全面理解的要求以及嘈杂的输出空间。在本论文中,我们通过以随机方式明确地对运动进行建模并学习潜在空间中的时间动态,从而提出了解决这些挑战的解决方案。
translated by 谷歌翻译
Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving stateof-the-art results on recognition, detection, segmentation and retrieval. In this work we propose and evaluate several deep neural network architectures to combine image information across a video over longer time periods than previously attempted. We propose two methods capable of handling full length videos. The first method explores various convolutional temporal feature pooling architectures, examining the various design choices which need to be made when adapting a CNN for this task. The second proposed method explicitly models the video as an ordered sequence of frames. For this purpose we employ a recurrent neural network that uses Long Short-Term Memory (LSTM) cells which are connected to the output of the underlying CNN. Our best networks exhibit significant performance improvements over previously published results on the Sports 1 million dataset (73.1% vs. 60.9%) and the UCF-101 datasets with (88.6% vs. 88.0%) and without additional optical flow information (82.6% vs. 73.0%).
translated by 谷歌翻译
了解3D场景是自治代理的关键先决条件。最近,LIDAR和其他传感器已经以点云帧的时间序列形式提供了大量数据。在这项工作中,我们提出了一种新的问题 - 顺序场景流量估计(SSFE) - 该旨在预测给定序列中所有点云的3D场景流。这与先前研究的场景流程估计问题不同,这侧重于两个框架。我们介绍SPCM-NET架构,通过计算相邻点云之间的多尺度时空相关性,然后通过订单不变的复制单元计算多级时空相关性来解决这个问题。我们的实验评估证实,与仅使用两个框架相比,点云序列的复发处理导致SSFE明显更好。另外,我们证明可以有效地修改该方法,用于顺序点云预测(SPF),一种需要预测未来点云帧的相关问题。我们的实验结果是使用SSFE和SPF的新基准进行评估,包括合成和实时数据集。以前,场景流估计的数据集仅限于两个帧。我们为这些数据集提供非琐碎的扩展,用于多帧估计和预测。由于难以获得现实世界数据集的地面真理运动,我们使用自我监督的培训和评估指标。我们认为,该基准将在该领域的未来研究中关键。将可访问基准和型号的所有代码。
translated by 谷歌翻译
Video enhancement is a challenging problem, more than that of stills, mainly due to high computational cost, larger data volumes and the difficulty of achieving consistency in the spatio-temporal domain. In practice, these challenges are often coupled with the lack of example pairs, which inhibits the application of supervised learning strategies. To address these challenges, we propose an efficient adversarial video enhancement framework that learns directly from unpaired video examples. In particular, our framework introduces new recurrent cells that consist of interleaved local and global modules for implicit integration of spatial and temporal information. The proposed design allows our recurrent cells to efficiently propagate spatio-temporal information across frames and reduces the need for high complexity networks. Our setting enables learning from unpaired videos in a cyclic adversarial manner, where the proposed recurrent units are employed in all architectures. Efficient training is accomplished by introducing one single discriminator that learns the joint distribution of source and target domain simultaneously. The enhancement results demonstrate clear superiority of the proposed video enhancer over the state-of-the-art methods, in all terms of visual quality, quantitative metrics, and inference speed. Notably, our video enhancer is capable of enhancing over 35 frames per second of FullHD video (1080x1920).
translated by 谷歌翻译
对社会互动中人类行为的预测在社会机器人或人造化身的设计中具有重要的应用。在本文中,我们专注于互动的单峰表示,并建议以数据驱动的方式解决互动生成。特别是,我们将人类相互作用的产生模型为一个离散的多序列生成问题,并呈现社会互动,这是一种新型的对抗性架构,用于有条件的相互作用生成。我们的模型建立在复发的编码器 - 码头生成器网络和双流歧视器上,该网络共同评估了相互作用和单个动作序列的现实主义,并在不同的时间范围内运行。至关重要的是,关于相互作用参与者的上下文信息在代理之间共享,并在发电和歧视者评估过程中重新注射。实验表明,尽管处理低维数据,但SocialInteractiongan成功地产生了互动人的高现实主义动作序列,与复发和卷积的鉴别剂的多样性进行了比较,我们认为这项工作将构成第一块朝着更高的维度和多二世型和多二世型和多二世模构成的石头互动产生。评估是使用经典GAN指标进行的,我们专门适应离散的顺序数据。我们的模型被证明可以正确学习交互序列的动态,同时利用了全部可用动作范围。
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
创建视频是为了表达情感,交换信息和分享经验。视频合成很长时间以来一直吸引了研究人员。尽管视觉合成的进步驱动了迅速的进展,但大多数现有研究都集中在提高框架的质量和之间的过渡上,而在生成更长的视频方面几乎没有取得进展。在本文中,我们提出了一种基于3D-VQGAN和Transformers的方法,以生成具有数千帧的视频。我们的评估表明,我们的模型在16架视频剪辑中培训了来自UCF-101,Sky TimeLapse和Taichi-HD数据集等标准基准测试片段,可以生成多样化,连贯和高质量的长视频。我们还展示了我们通过将时间信息与文本和音频结合在一起来生成有意义的长视频的方法的条件扩展。可以在https://songweige.github.io/projects/tats/index.html上找到视频和代码。
translated by 谷歌翻译
Giving machines the ability to imagine possible new objects or scenes from linguistic descriptions and produce their realistic renderings is arguably one of the most challenging problems in computer vision. Recent advances in deep generative models have led to new approaches that give promising results towards this goal. In this paper, we introduce a new method called DiCoMoGAN for manipulating videos with natural language, aiming to perform local and semantic edits on a video clip to alter the appearances of an object of interest. Our GAN architecture allows for better utilization of multiple observations by disentangling content and motion to enable controllable semantic edits. To this end, we introduce two tightly coupled networks: (i) a representation network for constructing a concise understanding of motion dynamics and temporally invariant content, and (ii) a translation network that exploits the extracted latent content representation to actuate the manipulation according to the target description. Our qualitative and quantitative evaluations demonstrate that DiCoMoGAN significantly outperforms existing frame-based methods, producing temporally coherent and semantically more meaningful results.
translated by 谷歌翻译
以对象为中心的表示是通过提供柔性抽象可以在可以建立的灵活性抽象来实现更系统的推广的有希望的途径。最近的简单2D和3D数据集的工作表明,具有对象的归纳偏差的模型可以学习段,并代表单独的数据的统计结构中的有意义对象,而无需任何监督。然而,尽管使用越来越复杂的感应偏差(例如,用于场景的尺寸或3D几何形状),但这种完全无监督的方法仍然无法扩展到不同的现实数据。在本文中,我们采取了弱监督的方法,并专注于如何使用光流的形式的视频数据的时间动态,2)调节在简单的对象位置上的模型可以用于启用分段和跟踪对象在明显更现实的合成数据中。我们介绍了一个顺序扩展,以便引入我们训练的推出,我们训练用于预测现实看的合成场景的光流,并显示调节该模型的初始状态在一小组提示,例如第一帧中的物体的质量中心,是足以显着改善实例分割。这些福利超出了新型对象,新颖背景和更长的视频序列的培训分配。我们还发现,在推论期间可以使用这种初始状态调节作为对特定物体或物体部分的型号查询模型,这可能会为一系列弱监管方法铺平,并允许更有效的互动训练有素的型号。
translated by 谷歌翻译
Despite recent progress in generative image modeling, successfully generating high-resolution, diverse samples from complex datasets such as ImageNet remains an elusive goal. To this end, we train Generative Adversarial Networks at the largest scale yet attempted, and study the instabilities specific to such scale. We find that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input. Our modifications lead to models which set the new state of the art in class-conditional image synthesis. When trained on ImageNet at 128×128 resolution, our models (BigGANs) achieve an Inception Score (IS) of 166.5 and Fréchet Inception Distance (FID) of 7.4, improving over the previous best IS of 52.52 and FID of 18.65.
translated by 谷歌翻译
现代计算机视觉已超越了互联网照片集的领域,并进入了物理世界,通过非结构化的环境引导配备摄像头的机器人和自动驾驶汽车。为了使这些体现的代理与现实世界对象相互作用,相机越来越多地用作深度传感器,重建了各种下游推理任务的环境。机器学习辅助的深度感知或深度估计会预测图像中每个像素的距离。尽管已经在深入估算中取得了令人印象深刻的进步,但仍然存在重大挑战:(1)地面真相深度标签很难大规模收集,(2)通常认为相机信息是已知的,但通常是不可靠的,并且(3)限制性摄像机假设很常见,即使在实践中使用了各种各样的相机类型和镜头。在本论文中,我们专注于放松这些假设,并描述将相机变成真正通用深度传感器的最终目标的贡献。
translated by 谷歌翻译
动态对象对机器人对环境的看法产生了重大影响,这降低了本地化和映射等基本任务的性能。在这项工作中,我们通过在由动态对象封闭的区域中合成合理的颜色,纹理和几何形状来解决这个问题。我们提出了一种新的几何感知Dynafill架构,其遵循粗略拓扑,并将我们所通用的经常性反馈机制结合到自适应地融合来自之前的时间步来的信息。我们使用对抗性培训来优化架构,以综合精细的现实纹理,使其能够以空间和时间相干的方式在线在线遮挡地区的幻觉和深度结构,而不依赖于未来的帧信息。将我们的待遇问题作为图像到图像到图像的翻译任务,我们的模型还纠正了与场景中动态对象的存在相关的区域,例如阴影或反射。我们引入了具有RGB-D图像,语义分段标签,摄像机的大型高估数据集,以及遮挡区域的地面RGB-D信息。广泛的定量和定性评估表明,即使在挑战天气条件下,我们的方法也能实现最先进的性能。此外,我们使用综合图像显示基于检索的视觉本地化的结果,该图像证明了我们方法的效用。
translated by 谷歌翻译
We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into spatial-temporal visual tokens and propose an embedding method for masked video token modeling to facilitate multi-task learning. We conduct extensive experiments to demonstrate the quality, efficiency, and flexibility of MAGVIT. Our experiments show that (i) MAGVIT performs favorably against state-of-the-art approaches and establishes the best-published FVD on three video generation benchmarks, including the challenging Kinetics-600. (ii) MAGVIT outperforms existing methods in inference time by two orders of magnitude against diffusion models and by 60x against autoregressive models. (iii) A single MAGVIT model supports ten diverse generation tasks and generalizes across videos from different visual domains. The source code and trained models will be released to the public at https://magvit.cs.cmu.edu.
translated by 谷歌翻译
生成模型已成为许多图像合成和编辑任务的基本构件。该领域的最新进展还使得能够生成具有多视图或时间一致性的高质量3D或视频内容。在我们的工作中,我们探索了学习无条件生成3D感知视频的4D生成对抗网络(GAN)。通过将神经隐式表示与时间感知歧视器相结合,我们开发了一个GAN框架,该框架仅通过单眼视频进行监督的3D视频。我们表明,我们的方法学习了可分解的3D结构和动作的丰富嵌入,这些结构和动作可以使时空渲染的新视觉效果,同时以与现有3D或视频gan相当的质量产生图像。
translated by 谷歌翻译
Visual signals in a video can be divided into content and motion. While content specifies which objects are in the video, motion describes their dynamics. Based on this prior, we propose the Motion and Content decomposed Generative Adversarial Network (MoCoGAN) framework for video generation. The proposed framework generates a video by mapping a sequence of random vectors to a sequence of video frames. Each random vector consists of a content part and a motion part. While the content part is kept fixed, the motion part is realized as a stochastic process. To learn motion and content decomposition in an unsupervised manner, we introduce a novel adversarial learning scheme utilizing both image and video discriminators. Extensive experimental results on several challenging datasets with qualitative and quantitative comparison to the state-of-theart approaches, verify effectiveness of the proposed framework. In addition, we show that MoCoGAN allows one to generate videos with same content but different motion as well as videos with different content and same motion.
translated by 谷歌翻译