We propose the Encoder-Recurrent-Decoder (ERD) model for recognition and prediction of human body pose in videos and motion capture. The ERD model is a recurrent neural network that incorporates nonlinear encoder and decoder networks before and after recurrent layers. We test instantiations of ERD architectures in the tasks of motion capture (mocap) generation, body pose labeling and body pose forecasting in videos. Our model handles mocap training data across multiple subjects and activity domains, and synthesizes novel motions while avoiding drifting for long periods of time. For human pose labeling, ERD outperforms a per frame body part detector by resolving left-right body part confusions. For video pose forecasting, ERD predicts body joint displacements across a temporal horizon of 400ms and outperforms a first order motion model based on optical flow. ERDs extend previous Long Short Term Memory (LSTM) models in the literature to jointly learn representations and their dynamics. Our experiments show such representation learning is crucial for both labeling and prediction in space-time. We find this is a distinguishing feature between the spatio-temporal visual domain in comparison to 1D text, speech or handwriting, where straightforward hard coded representations have shown excellent results when directly combined with recurrent units [31] .
translated by 谷歌翻译
Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented reality. Following the success of deep learning methods in several computer vision tasks, recent work has focused on using deep recurrent neural networks (RNNs) to model human motion, with the goal of learning time-dependent representations that perform tasks such as short-term motion prediction and long-term human motion synthesis. We examine recent work, with a focus on the evaluation methodologies commonly used in the literature, and show that, surprisingly, state-of-the-art performance can be achieved by a simple baseline that does not attempt to model motion at all. We investigate this result, and analyze recent RNN methods by looking at the architectures, loss functions, and training procedures used in state-of-the-art approaches. We propose three changes to the standard RNN models typically used for human motion, which result in a simple and scalable RNN architecture that obtains state-of-the-art performance on human motion prediction.
translated by 谷歌翻译
预测历史姿势序列的人类运动对于机器具有成功与人类智能相互作用的关键。到目前为止已经避免的一个方面是,我们代表骨骼姿势的事实是对预测结果的关键影响。然而,没有努力调查不同的姿势代表方案。我们对各种姿势表示进行了深入研究,重点关注它们对运动预测任务的影响。此外,最近的方法在现成的RNN单位上构建,用于运动预测。这些方法在捕获长期依赖性方面,顺序地并固有地具有困难。在本文中,我们提出了一种新颖的RNN架构,用于运动预测的AHMR(殷勤分层运动复发网络),其同时模拟局部运动上下文和全局上下文。我们进一步探索了运动预测任务的测地损失和前向运动学损失,其具有比广泛采用的L2损耗更多的几何意义。有趣的是,我们将我们的方法应用于一系列铰接物对象,包括人类,鱼类和鼠标。经验结果表明,我们的方法在短期预测中占据了最先进的方法,实现了大量增强的长期预测熟练程度,例如在50秒的预测中保留自然人样的运动。我们的代码已发布。
translated by 谷歌翻译
在这项工作中,我们提出了MotionMixer,这是一个有效的3D人体姿势预测模型,仅基于多层感知器(MLP)。MotionMixer通过顺序混合这两种方式来学习时空3D身体姿势依赖性。给定3D身体姿势的堆叠序列,空间MLP提取物是身体关节的细粒空间依赖性。然后,随着时间的推移,身体关节的相互作用由时间MLP建模。最终将时空混合特征汇总并解码以获得未来的运动。为了校准姿势序列中每个时间步的影响,我们利用挤压和兴奋(SE)块。我们使用标准评估协议评估了36M,Amass和3DPW数据集的方法。对于所有评估,我们展示了最先进的性能,同时具有具有较少参数的模型。我们的代码可在以下网址找到:https://github.com/motionmlp/motionmixer
translated by 谷歌翻译
本文认为共同解决估计3D人体的高度相关任务,并从RGB图像序列预测未来的3D运动。基于Lie代数姿势表示,提出了一种新的自投影机制,自然保留了人类运动运动学。通过基于编码器 - 解码器拓扑的序列到序列的多任务架构进一步促进了这一点,这使我们能够利用两个任务共享的公共场所。最后,提出了一个全球细化模块来提高框架的性能。我们的方法称为PoMomemet的效力是通过消融测试和人文3.6M和Humaneva-I基准的实证评估,从而获得与最先进的竞争性能。
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
人类行动识别是计算机视觉中的重要应用领域。它的主要目的是准确地描述人类的行为及其相互作用,从传感器获得的先前看不见的数据序列中。识别,理解和预测复杂人类行动的能力能够构建许多重要的应用,例如智能监视系统,人力计算机界面,医疗保健,安全和军事应用。近年来,计算机视觉社区特别关注深度学习。本文使用深度学习技术的视频分析概述了当前的动作识别最新识别。我们提出了识别人类行为的最重要的深度学习模型,并分析它们,以提供用于解决人类行动识别问题的深度学习算法的当前进展,以突出其优势和缺点。基于文献中报道的识别精度的定量分析,我们的研究确定了动作识别中最新的深层体系结构,然后为该领域的未来工作提供当前的趋势和开放问题。
translated by 谷歌翻译
Figure 1: Given challenging in-the-wild videos, a recent state-of-the-art video-pose-estimation approach [31] (top), fails to produce accurate 3D body poses. To address this, we exploit a large-scale motion-capture dataset to train a motion discriminator using an adversarial approach. Our model (VIBE) (bottom) is able to produce realistic and accurate pose and shape, outperforming previous work on standard benchmarks.
translated by 谷歌翻译
From an image of a person in action, we can easily guess the 3D motion of the person in the immediate past and future. This is because we have a mental model of 3D human dynamics that we have acquired from observing visual sequences of humans in motion. We present a framework that can similarly learn a representation of 3D dynamics of humans from video via a simple but effective temporal encoding of image features. At test time, from video, the learned temporal representation give rise to smooth 3D mesh predictions. From a single image, our model can recover the current 3D mesh as well as its 3D past and future motion. Our approach is designed so it can learn from videos with 2D pose annotations in a semi-supervised manner. Though annotated data is always limited, there are millions of videos uploaded daily on the Internet. In this work, we harvest this Internet-scale source of unlabeled data by training our model on unlabeled video with pseudo-ground truth 2D pose obtained from an off-the-shelf 2D pose detector. Our experiments show that adding more videos with pseudo-ground truth 2D pose monotonically improves 3D prediction performance. We evaluate our model, Human Mesh and Motion Recovery (HMMR), on the recent challenging dataset of 3D Poses in the Wild and obtain state-of-the-art performance on the 3D prediction task without any fine-tuning. The project website with video, code, and data can be found at https://akanazawa.github.io/ human_dynamics/.
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
我们的目标是从规定的行动类别中解决从规定的行动类别创造多元化和自然人动作视频的有趣但具有挑战性的问题。关键问题在于能够在视觉外观中综合多种不同的运动序列。在本文中通过两步过程实现,该两步处理维持内部3D姿势和形状表示,Action2Motion和Motion2Video。 Action2Motion随机生成规定的动作类别的合理的3D姿势序列,该类别由Motion2Video进行处理和呈现,以形成2D视频。具体而言,Lie代数理论从事人类运动学的物理法之后代表自然人动作;开发了一种促进输出运动的分集的时间变化自动编码器(VAE)。此外,给定衣服人物的额外输入图像,提出了整个管道以提取他/她的3D详细形状,并在视频中呈现来自不同视图的合理运动。这是通过改进从单个2D图像中提取3D人类形状和纹理,索引,动画和渲染的现有方法来实现这一点,以形成人类运动的2D视频。它还需要3D人类运动数据集的策策和成果进行培训目的。彻底的经验实验,包括消融研究,定性和定量评估表现出我们的方法的适用性,并展示了解决相关任务的竞争力,其中我们的方法的组成部分与最先进的方式比较。
translated by 谷歌翻译
“我们怎样才能通过简单地告诉他们,从动画电影剧本或移动机器人的3D角色我们希望他们做什么?” “我们如何非结构化和复杂的可以造一个句子,仍然从其生成合理的运动?”这些都是需要在长期得到回答,因为领域仍然处于起步阶段的问题。通过这些问题的启发,我们提出了产生成分操作的新技术,它可以处理复杂的输入句子。我们的产量是描绘在输入句子中的动作三维姿态序列。我们提出了一个分级二流顺序模型,探讨对应于给定的运动自然语言中的句子和三维姿态序列之间的精细联合级映射。我们学习运动的两个集管表示 - 每一个上半身下半身动作。我们的模型可以生成简短的句子描述单个动作以及长组成的句子描述多个连续叠加行动似是而非的姿势序列。我们评估的公开可用的KIT运动语言数据集含有与人类标注的句子3D姿势数据我们提出的模型。实验结果表明,我们的模型以50%的余量前进的状态的最先进的在客观评价基于文本的运动的合成。基于用户研究定性评价表明我们的合成运动被认为是最接近地面实况动作捕捉短期和组成句子。
translated by 谷歌翻译
人类姿势预测是一个充满挑战的问题,涉及复杂的人体运动和姿势动态。在环境中有多个人的情况下,一个人的运动也可能受到他人的运动和动态运动的影响。尽管以前有一些针对多人动态姿势预测问题的作品,但它们通常将整个姿势序列作为时间序列(忽略关节之间的基本关系)建模,或者仅一次输出一个人的未来姿势序列。在本文中,我们提出了一种新方法,称为社会运动变压器(SOM形态),用于多人3D姿势预测。我们的变压器架构独特地将人类运动输入作为关节序列而不是时间序列建模,从而使我们能够对关节进行注意,同时预测并联每个关节的整个未来运动序列。我们表明,通过这种问题重新进行,Somoformer自然会通过使用场景中所有人的关节作为输入查询来扩展到多人场景。我们的模型使用学识渊博的嵌入来表示关节,人身份和全球地位的类型,了解关节之间和人之间的关系,更强烈地参加了来自同一或附近的人的关节。 Somoformer的表现优于SOMOF基准以及CMU-MOCAP和MUPOTS-3D数据集的长期运动预测的最先进方法。出版后将提供代码。
translated by 谷歌翻译
长期人体运动预测对于安全关键应用是必不可少的,例如人机互动和自主驾驶。在本文中,我们展示了实现长期预测,预测每次瞬间的人类姿势是不必要的。相反,通过线性地插入键盘来预测几个小折叠和近似中间组更有效。我们将证明我们的方法使我们能够在未来预测最多5秒的现实运动,远远大于文献中遇到的典型1秒。此外,由于我们模拟了未来的重叠概率,因此我们可以通过在推理时间采样来产生多种合理的未来动作。在这个延长的时间内,我们的预测更加现实,更多样化,更好地保护运动动力学而不是那些最先进的方法产量。
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
培训视频中人类姿势估计的最先进模型需要具有很难获得的注释的数据集。尽管最近已将变压器用于身体姿势序列建模,但相关方法依靠伪地真相来增强目前有限的培训数据可用于学习此类模型。在本文中,我们介绍了Posebert,Posebert是一个通过掩盖建模对3D运动捕获(MOCAP)数据进行全面训练的变压器模块。它是简单,通用和通用的,因为它可以插入任何基于图像的模型的顶部,以在基于视频的模型中使用时间信息。我们展示了Posebert的变体,不同的输入从3D骨骼关键点到全身或仅仅是手(Mano)的3D参数模型的旋转。由于Posebert培训是任务不可知论的,因此该模型可以应用于姿势细化,未来的姿势预测或运动完成等几个任务。我们的实验结果验证了在各种最新姿势估计方法之上添加Posebert始终提高其性能,而其低计算成本使我们能够在实时演示中使用它,以通过A的机器人手使机器人手通过摄像头。可以在https://github.com/naver/posebert上获得测试代码和型号。
translated by 谷歌翻译
由于价格合理的可穿戴摄像头和大型注释数据集的可用性,在过去几年中,Egintric Vision(又名第一人称视觉-FPV)的应用程序在过去几年中蓬勃发展。可穿戴摄像机的位置(通常安装在头部上)允许准确记录摄像头佩戴者在其前面的摄像头,尤其是手和操纵物体。这种内在的优势可以从多个角度研究手:将手及其部分定位在图像中;了解双手涉及哪些行动和活动;并开发依靠手势的人类计算机界面。在这项调查中,我们回顾了使用以自我为中心的愿景专注于手的文献,将现有方法分类为:本地化(其中的手或部分在哪里?);解释(手在做什么?);和应用程序(例如,使用以上为中心的手提示解决特定问题的系统)。此外,还提供了带有手基注释的最突出的数据集的列表。
translated by 谷歌翻译
在本文中,我们提出了一种新的方法来增强从单个可佩戴相机捕获的视频计算的人的3D身体姿势估计。关键的想法是利用在联合嵌入空间中链接第一和第三次视图的高级功能。为了了解这样的嵌入空间,我们介绍了First2第三姿势,这是一个近2,000个视频的新配对同步数据集,描绘了从第一和第三视角捕获的人类活动。我们明确地考虑了空间和运动域功能,同时使用以自我监督的方式培训的半暹罗架构。实验结果表明,使用我们的数据集学习的联合多视图嵌入式空间可用于从任意单视图的自拍视频中提取歧视特征,而无需需要域适应,也不知道相机参数。在三种监督最先进的方法中,我们在两个无约束数据集中实现了重大改善了两个无约束的数据集。我们的数据集和代码将可用于研究目的。
translated by 谷歌翻译
Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise. We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and demonstrate the value of these models on benchmark video recognition tasks, image description and retrieval problems, and video narration challenges. In contrast to current models which assume a fixed spatio-temporal receptive field or simple temporal averaging for sequential processing, recurrent convolutional models are "doubly deep" in that they can be compositional in spatial and temporal "layers". Such models may have advantages when target concepts are complex and/or training data are limited. Learning long-term dependencies is possible when nonlinearities are incorporated into the network state updates. Long-term RNN models are appealing in that they directly can map variable-length inputs (e.g., video frames) to variable length outputs (e.g., natural language text) and can model complex temporal dynamics; yet they can be optimized with backpropagation. Our recurrent long-term models are directly connected to modern visual convnet models and can be jointly trained to simultaneously learn temporal dynamics and convolutional perceptual representations. Our results show such models have distinct advantages over state-of-the-art models for recognition or generation which are separately defined and/or optimized.
translated by 谷歌翻译
We present a new method for generating controllable, dynamically responsive, and photorealistic human animations. Given an image of a person, our system allows the user to generate Physically plausible Upper Body Animation (PUBA) using interaction in the image space, such as dragging their hand to various locations. We formulate a reinforcement learning problem to train a dynamic model that predicts the person's next 2D state (i.e., keypoints on the image) conditioned on a 3D action (i.e., joint torque), and a policy that outputs optimal actions to control the person to achieve desired goals. The dynamic model leverages the expressiveness of 3D simulation and the visual realism of 2D videos. PUBA generates 2D keypoint sequences that achieve task goals while being responsive to forceful perturbation. The sequences of keypoints are then translated by a pose-to-image generator to produce the final photorealistic video.
translated by 谷歌翻译