Stochastic human motion prediction aims to forecast multiple plausible future motions given a single pose sequence from the past. Most previous works focus on designing elaborate losses to improve the accuracy, while the diversity is typically characterized by randomly sampling a set of latent variables from the latent prior, which is then decoded into possible motions. This joint training of sampling and decoding, however, suffers from posterior collapse as the learned latent variables tend to be ignored by a strong decoder, leading to limited diversity. Alternatively, inspired by the diffusion process in nonequilibrium thermodynamics, we propose MotionDiff, a diffusion probabilistic model to treat the kinematics of human joints as heated particles, which will diffuse from original states to a noise distribution. This process offers a natural way to obtain the "whitened" latents without any trainable parameters, and human motion prediction can be regarded as the reverse diffusion process that converts the noise distribution into realistic future motions conditioned on the observed sequence. Specifically, MotionDiff consists of two parts: a spatial-temporal transformer-based diffusion network to generate diverse yet plausible motions, and a graph convolutional network to further refine the outputs. Experimental results on two datasets demonstrate that our model yields the competitive performance in terms of both accuracy and diversity.
translated by 谷歌翻译
最近在随机运动预测中的进展,即预测单一过去的姿势序列的多个可能的未来人类动作,导致产生真正不同的未来动作,甚至可以控制一些身体部位的运动。然而,为了实现这一点,最先进的方法需要学习用于多样性的多个映射和用于可控运动预测的专用模型。在本文中,我们向统一的深度生成网络介绍了多种和可控的运动预测。为此,我们利用了现实人类动作的直觉由有效姿势的平滑序列组成,并且给定的有限数据,学习姿势比动作更具易行。因此,我们设计了一种发电机,其顺序地预测不同车身部件的运动,并引入基于流动的基于流动的姿势,以及接合角度损失,以实现运动现实主义。在两个标准基准数据集,人类3.6m和人文集上进行实验。我展示了我们的方法在样本多样性和准确性方面优于最先进的基线。该代码可在https://github.com/wei-mao-2019/gsps获得
translated by 谷歌翻译
合理和可控3D人类运动动画的创建是一个长期存在的问题,需要对技术人员艺术家进行手动干预。目前的机器学习方法可以半自动化该过程,然而,它们以显着的方式受到限制:它们只能处理预期运动的单个轨迹,该轨迹排除了对输出的细粒度控制。为了缓解该问题,我们在多个轨迹表示为具有缺失关节的姿势的空间和时间内将未来姿态预测的问题重构为姿势完成。我们表明这种框架可以推广到设计用于未来姿态预测的其他神经网络。曾经在该框架中培训,模型能够从任何数量的轨迹预测序列。我们提出了一种新颖的变形金刚架构,Trajevae,在这个想法上建立了一个,为3D人类动画提供了一个多功能框架。我们展示了Trajevae提供比基于轨迹的参考方法和方法基于过去的姿势。我们还表明,即使仅提供初始姿势,它也可以预测合理的未来姿势。
translated by 谷歌翻译
Monocular 3D human pose estimation is quite challenging due to the inherent ambiguity and occlusion, which often lead to high uncertainty and indeterminacy. On the other hand, diffusion models have recently emerged as an effective tool for generating high-quality images from noise. Inspired by their capability, we explore a novel pose estimation framework (DiffPose) that formulates 3D pose estimation as a reverse diffusion process. We incorporate novel designs into our DiffPose that facilitate the diffusion process for 3D pose estimation: a pose-specific initialization of pose uncertainty distributions, a Gaussian Mixture Model-based forward diffusion process, and a context-conditioned reverse diffusion process. Our proposed DiffPose significantly outperforms existing methods on the widely used pose estimation benchmarks Human3.6M and MPI-INF-3DHP.
translated by 谷歌翻译
人类运动建模对于许多现代图形应用非常重要,这些应用通常需要专业技能。为了消除外行的技能障碍,最近的运动生成方法可以直接产生以自然语言为条件的人类动作。但是,通过各种文本输入,实现多样化和细粒度的运动产生,仍然具有挑战性。为了解决这个问题,我们提出了MotionDiffuse,这是第一个基于基于文本模型的基于文本驱动的运动生成框架,该框架证明了现有方法的几种期望属性。 1)概率映射。 MotionDiffuse不是确定性的语言映射,而是通过一系列注入变化的步骤生成动作。 2)现实的综合。 MotionDiffuse在建模复杂的数据分布和生成生动的运动序列方面表现出色。 3)多级操作。 Motion-Diffuse响应有关身体部位的细粒度指示,以及随时间变化的文本提示,任意长度运动合成。我们的实验表明,Motion-Diffuse通过说服文本驱动运动产生和动作条件运动的运动来优于现有的SOTA方法。定性分析进一步证明了MotionDiffuse对全面运动产生的可控性。主页:https://mingyuan-zhang.github.io/projects/motiondiffuse.html
translated by 谷歌翻译
本文解决了人类运动预测的问题,包括预测未来的身体从历史上观察到的序列构成的构成。尽管其性能,但当前的最新方法依赖于任意复杂性的深度学习体系结构,例如经常性神经网络〜(RNN),变压器或图形卷积网络〜(GCN),通常需要多个培训阶段,等等。超过300万参数。在本文中,我们表明,这些方法的性能可以通过轻巧且纯粹的MLP体系结构超越,并且与几种标准实践(例如用离散的余弦变换代表身体姿势(DCT))相结合时,只有0.14亿个参数,预测关节的残留位移和优化速度作为辅助损失。对人类360万的详尽评估,Amass和3DPW数据集表明,我们的方法(我们将其配置为Simlpe)始终优于所有其他方法。我们希望我们的简单方法可以为社区提供强大的基准,并允许重新考虑人类运动预测的问题,以及当前的基准是否确实需要复杂的建筑设计。我们的代码可在\ url {https://github.com/dulucas/simlpe}上获得。
translated by 谷歌翻译
各种人类运动预测旨在从一系列观察到的姿势中预测多个可能的未来姿势序列。以前的方法通常采用深层生成网络来对数据的条件分布进行建模,然后从分布中随机取得结果。尽管可以获得不同的结果,但它们通常是最有多样化的结果。最近的工作明确地通过确定性网络了解条件分布的多种模式,但是,该网络只能涵盖有限范围内的固定数量模式。在本文中,我们提出了一种新型的抽样策略,用于对深层生成模型学到的不平衡多模式分布进行采样非常多样化的结果。我们的方法通过生成辅助空间,并巧妙地从目标分布中的多样采样从辅助空间中随机进行随机采样。我们提出了一种简单而有效的网络体系结构,该架构实现了这种新型的采样策略,该策略结合了gumbel-softmax系数矩阵采样方法和促进铰链损失函数的积极多样性。广泛的实验表明,与先前最新的采样方法相比,我们的方法显着提高了采样的多样性和准确性。代码和预训练模型可在https://github.com/droliven/diverse_sampling上找到。
translated by 谷歌翻译
Conventional methods for human motion synthesis are either deterministic or struggle with the trade-off between motion diversity and motion quality. In response to these limitations, we introduce MoFusion, i.e., a new denoising-diffusion-based framework for high-quality conditional human motion synthesis that can generate long, temporally plausible, and semantically accurate motions based on a range of conditioning contexts (such as music and text). We also present ways to introduce well-known kinematic losses for motion plausibility within the motion diffusion framework through our scheduled weighting strategy. The learned latent space can be used for several interactive motion editing applications -- like inbetweening, seed conditioning, and text-based editing -- thus, providing crucial abilities for virtual character animation and robotics. Through comprehensive quantitative evaluations and a perceptual user study, we demonstrate the effectiveness of MoFusion compared to the state of the art on established benchmarks in the literature. We urge the reader to watch our supplementary video and visit https://vcai.mpi-inf.mpg.de/projects/MoFusion.
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
Traditionally, monocular 3D human pose estimation employs a machine learning model to predict the most likely 3D pose for a given input image. However, a single image can be highly ambiguous and induces multiple plausible solutions for the 2D-3D lifting step which results in overly confident 3D pose predictors. To this end, we propose \emph{DiffPose}, a conditional diffusion model, that predicts multiple hypotheses for a given input image. In comparison to similar approaches, our diffusion model is straightforward and avoids intensive hyperparameter tuning, complex network structures, mode collapse, and unstable training. Moreover, we tackle a problem of the common two-step approach that first estimates a distribution of 2D joint locations via joint-wise heatmaps and consecutively approximates them based on first- or second-moment statistics. Since such a simplification of the heatmaps removes valid information about possibly correct, though labeled unlikely, joint locations, we propose to represent the heatmaps as a set of 2D joint candidate samples. To extract information about the original distribution from these samples we introduce our \emph{embedding transformer} that conditions the diffusion model. Experimentally, we show that DiffPose slightly improves upon the state of the art for multi-hypothesis pose estimation for simple poses and outperforms it by a large margin for highly ambiguous poses.
translated by 谷歌翻译
Thanks to the development of 2D keypoint detectors, monocular 3D human pose estimation (HPE) via 2D-to-3D uplifting approaches have achieved remarkable improvements. Still, monocular 3D HPE is a challenging problem due to the inherent depth ambiguities and occlusions. To handle this problem, many previous works exploit temporal information to mitigate such difficulties. However, there are many real-world applications where frame sequences are not accessible. This paper focuses on reconstructing a 3D pose from a single 2D keypoint detection. Rather than exploiting temporal information, we alleviate the depth ambiguity by generating multiple 3D pose candidates which can be mapped to an identical 2D keypoint. We build a novel diffusion-based framework to effectively sample diverse 3D poses from an off-the-shelf 2D detector. By considering the correlation between human joints by replacing the conventional denoising U-Net with graph convolutional network, our approach accomplishes further performance improvements. We evaluate our method on the widely adopted Human3.6M and HumanEva-I datasets. Comprehensive experiments are conducted to prove the efficacy of the proposed method, and they confirm that our model outperforms state-of-the-art multi-hypothesis 3D HPE methods.
translated by 谷歌翻译
Generating realistic motions for digital humans is a core but challenging part of computer animations and games, as human motions are both diverse in content and rich in styles. While the latest deep learning approaches have made significant advancements in this domain, they mostly consider motion synthesis and style manipulation as two separate problems. This is mainly due to the challenge of learning both motion contents that account for the inter-class behaviour and styles that account for the intra-class behaviour effectively in a common representation. To tackle this challenge, we propose a denoising diffusion probabilistic model solution for styled motion synthesis. As diffusion models have a high capacity brought by the injection of stochasticity, we can represent both inter-class motion content and intra-class style behaviour in the same latent. This results in an integrated, end-to-end trained pipeline that facilitates the generation of optimal motion and exploration of content-style coupled latent space. To achieve high-quality results, we design a multi-task architecture of diffusion model that strategically generates aspects of human motions for local guidance. We also design adversarial and physical regulations for global guidance. We demonstrate superior performance with quantitative and qualitative results and validate the effectiveness of our multi-task architecture.
translated by 谷歌翻译
我们提出了一个隐式神经表示,以学习运动运动运动的时空空间。与以前代表运动为离散顺序样本的工作不同,我们建议将广泛的运动空间随着时间的流逝表达为连续函数,因此名称为神经运动场(NEMF)。具体来说,我们使用神经网络来学习此功能,以用于杂项运动集,该动作旨在以时间坐标为$ t $的生成模型和用于控制样式的随机矢量$ z $。然后,将模型作为变异自动编码器(VAE)进行训练,并带有运动编码器来采样潜在空间。我们使用多样化的人类运动数据集和四倍的数据集训练模型,以证明其多功能性,并最终将其部署为通用运动,然后再解决任务 - 静态问题,并在不同的运动生成和编辑应用中显示出优势,例如运动插值,例如运动插值,例如 - 上映和重新散布。可以在我们的项目页面上找到更多详细信息:https://cs.yale.edu/homes/che/projects/nemf/
translated by 谷歌翻译
Denoising diffusion probabilistic models are a promising new class of generative models that mark a milestone in high-quality image generation. This paper showcases their ability to sequentially generate video, surpassing prior methods in perceptual and probabilistic forecasting metrics. We propose an autoregressive, end-to-end optimized video diffusion model inspired by recent advances in neural video compression. The model successively generates future frames by correcting a deterministic next-frame prediction using a stochastic residual generated by an inverse diffusion process. We compare this approach against five baselines on four datasets involving natural and simulation-based videos. We find significant improvements in terms of perceptual quality for all datasets. Furthermore, by introducing a scalable version of the Continuous Ranked Probability Score (CRPS) applicable to video, we show that our model also outperforms existing approaches in their probabilistic frame forecasting ability.
translated by 谷歌翻译
先前关于人类运动预测的工作遵循观察到的序列与要预测的序列之间建立映射关系的模式。但是,由于多元时间序列数据的固有复杂性,找到运动序列之间的外推关系仍然是一个挑战。在本文中,我们提出了一种新的预测模式,该模式介绍了以前被忽视的人类姿势,以从插值的角度实施预测任务。这些姿势在预测序列后存在,并形成特权序列。要具体而言,我们首先提出了一个插值学习网络(ITP-NETWORK),该网络既编码观察到的序列和特权序列,以插入预测的序列之间,其中嵌入式的特权序列 - 编码器(Priv-incoder)学习了这些序列特权知识(PK)同时。然后,我们提出了一个最终的预测网络(FP-NETWORK),该网络无法观察到特权序列,但配备了一种新型的PK模拟器,该序列可以提取从先前的网络中学到的PK。该模拟器作为输入观察到的序列,但近似私有编码器的行为,从而使fp-network模仿插值过程。广泛的实验结果表明,在短期和长期预测中,我们的预测模式在基准的H.36M,CMU-MOCAP和3DPW数据集上实现了最先进的性能。
translated by 谷歌翻译
运动预测是计算机视觉中的经典问题,其旨在预测观察到的姿势序列的未来运动。已经提出了各种深度学习模型,在运动预测上实现了最先进的性能。然而,现有方法通常专注于在姿势空间中建模时间动态。不幸的是,人类运动的复杂和高度的性质带来了动态背景捕获的固有挑战。因此,我们远离传统的基于姿势的表示,并提出采用各个关节的相空间轨迹表示的新方法。此外,目前的方法倾向于仅考虑物理连接的关节之间的依赖性。在本文中,我们介绍了一种小说卷积神经模型,以有效利用明确的运动解剖学知识,并同时捕获关节轨迹动态的空间和时间信息。然后,我们提出了一个全局优化模块,了解各个联合功能之间的隐式关系。经验上,我们的方法在大规模3D人体运动基准数据集(即,Human3.6m,CMU Mocap)上进行评估。这些结果表明,我们的方法在基准数据集中设置了新的最先进状态。我们的代码将在https://github.com/post-group/teid中提供。
translated by 谷歌翻译
手语制作(SLP)旨在将口语语言自动转化为符号序列。 SLP的核心过程是将符号光泽序列转换为其相应的标志姿势序列(G2P)。大多数现有的G2P模型通常以自回归方式执行这种条件的远程生成,这不可避免地导致错误的积累。为了解决这个问题,我们提出了一种量化量子序列序列的生成的矢量量化扩散方法,称为poseVQ扩散,这是一种迭代性非自动入学方法。具体而言,我们首先引入量化量化变量自动编码器(姿势VQVAE)模型,以表示姿势序列作为一系列潜在代码。然后,我们通过最近开发的扩散体系结构的扩展来对潜在离散空间进行建模。为了更好地利用时空信息,我们介绍了一种新颖的体系结构,即CodeUnet,以在离散空间中生成更高质量的姿势序列。此外,利用学习的代码,我们开发了一种新型的顺序k-nearest-neighbours方法,以预测相应的光泽序列的姿势序列的可变长度。因此,与自回旋G2P模型相比,我们的模型具有更快的采样速度,并产生明显更好的结果。与以前的非自动入学G2P方法相比,PoseVQ扩散通过迭代改进改善了预测的结果,从而在SLP评估基准上获得了最新的结果。
translated by 谷歌翻译
在计算机视觉中起关键作用的人类运动预测通常需要过去的运动序列作为输入。但是,在实际应用中,完整而正确的过去运动顺序可能太贵了。在本文中,我们提出了一种新的方法,可以从更弱的条件(即单个图像)中预测未来的人类运动,并具有混合密度网络(MDN)建模。与大多数现有的深层人类运动预测方法相反,MDN的多模式性质可以产生各种未来的运动假设,这很好地补偿了由单个输入和人类运动不确定性汇总的强烈随机歧义。在设计损失函数时,我们进一步引入了基于能量的公式,以灵活地对MDN的可学习参数施加先前的损失,以保持运动相干性,并通过自定义能量功能来提高预测准确性。我们训练有素的模型将图像直接作为输入,并生成满足给定条件的多个合理动作。在两个标准基准数据集上进行的广泛实验证明了我们方法在预测多样性和准确性方面的有效性。
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
多人运动预测仍然是一个具有挑战性的问题,尤其是在个人运动和社会互动的共同表示中。大多数先前的方法仅涉及学习局部姿势动态以进行单个运动(没有全球身体轨迹),并难以捕获社交互动的复杂互动依赖性。在本文中,我们提出了一种新颖的社会意识运动变压器(SOM形态),以共同的方式有效地模拟个人运动和社会互动。具体而言,Somoformer提取了位移轨迹空间中子序列的运动特征,以有效地学习每个人的局部和全局姿势动力学。此外,我们设计了一种新型的SOM机制中新型的社交运动注意机制,以通过跨时间和社会维度的运动相似性计算同时优化动态表示并捕获相互作用依赖性。在短期和长期视野上,我们在多人运动数据集上进行了经验评估我们的框架,并证明我们的方法极大地优于单人和多人运动预测的最先进方法。接受后将公开提供代码。
translated by 谷歌翻译