Generative modeling of human motion has broad applications in computer animation, virtual reality, and robotics. Conventional approaches develop separate models for different motion synthesis tasks, and typically use a model of a small size to avoid overfitting the scarce data available in each setting. It remains an open question whether developing a single unified model is feasible, which may 1) benefit the acquirement of novel skills by combining skills learned from multiple tasks, and 2) help in increasing the model capacity without overfitting by combining multiple data sources. Unification is challenging because 1) it involves diverse control signals as well as targets of varying granularity, and 2) motion datasets may use different skeletons and default poses. In this paper, we present MoFusion, a framework for unified motion synthesis. MoFusion employs a Transformer backbone to ease the inclusion of diverse control signals via cross attention, and pretrains the backbone as a diffusion model to support multi-granularity synthesis ranging from motion completion of a body part to whole-body motion generation. It uses a learnable adapter to accommodate the differences between the default skeletons used by the pretraining and the fine-tuning data. Empirical results show that pretraining is vital for scaling the model size without overfitting, and demonstrate MoFusion's potential in various tasks, e.g., text-to-motion, motion completion, and zero-shot mixing of multiple control signals. Project page: \url{https://ofa-sys.github.io/MoFusion/}.
translated by 谷歌翻译
We study a challenging task, conditional human motion generation, which produces plausible human motion sequences according to various conditional inputs, such as action classes or textual descriptors. Since human motions are highly diverse and have a property of quite different distribution from conditional modalities, such as textual descriptors in natural languages, it is hard to learn a probabilistic mapping from the desired conditional modality to the human motion sequences. Besides, the raw motion data from the motion capture system might be redundant in sequences and contain noises; directly modeling the joint distribution over the raw motion sequences and conditional modalities would need a heavy computational overhead and might result in artifacts introduced by the captured noises. To learn a better representation of the various human motion sequences, we first design a powerful Variational AutoEncoder (VAE) and arrive at a representative and low-dimensional latent code for a human motion sequence. Then, instead of using a diffusion model to establish the connections between the raw motion sequences and the conditional inputs, we perform a diffusion process on the motion latent space. Our proposed Motion Latent-based Diffusion model (MLD) could produce vivid motion sequences conforming to the given conditional inputs and substantially reduce the computational overhead in both the training and inference stages. Extensive experiments on various human motion generation tasks demonstrate that our MLD achieves significant improvements over the state-of-the-art methods among extensive human motion generation tasks, with two orders of magnitude faster than previous diffusion models on raw motion sequences.
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
Generating controllable and editable human motion sequences is a key challenge in 3D Avatar generation. It has been labor-intensive to generate and animate human motion for a long time until learning-based approaches have been developed and applied recently. However, these approaches are still task-specific or modality-specific\cite {ahuja2019language2pose}\cite{ghosh2021synthesis}\cite{ferreira2021learning}\cite{li2021ai}. In this paper, we propose ``UDE", the first unified driving engine that enables generating human motion sequences from natural language or audio sequences (see Fig.~\ref{fig:teaser}). Specifically, UDE consists of the following key components: 1) a motion quantization module based on VQVAE that represents continuous motion sequence as discrete latent code\cite{van2017neural}, 2) a modality-agnostic transformer encoder\cite{vaswani2017attention} that learns to map modality-aware driving signals to a joint space, and 3) a unified token transformer (GPT-like\cite{radford2019language}) network to predict the quantized latent code index in an auto-regressive manner. 4) a diffusion motion decoder that takes as input the motion tokens and decodes them into motion sequences with high diversity. We evaluate our method on HumanML3D\cite{Guo_2022_CVPR} and AIST++\cite{li2021learn} benchmarks, and the experiment results demonstrate our method achieves state-of-the-art performance. Project website: \url{https://github.com/zixiangzhou916/UDE/
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
基于文本的运动生成模型正在引起人们对它们在游戏,动画或机器人行业中自动化运动过程的潜力的兴趣激增。在本文中,我们提出了一种基于扩散的运动合成和名为Flame的编辑模型。受扩散模型中最新成功的启发,我们将基于扩散的生成模型集成到运动域中。火焰可以产生与给定文本很好地对齐的高保真动作。此外,它可以编辑运动的各个部分,无论是在框架和联合方面,而无需进行任何微调。火焰涉及我们设计的新的基于变压器的架构,以更好地处理运动数据,这对于管理可变长度运动和良好的自由形式文本至关重要。在实验中,我们表明火焰在三个文本数据集上实现了最新的一代表演:HumanML3D,Babel和Kit。我们还证明,火焰的编辑能力可以扩展到其他任务,例如运动预测或运动内部,这些任务先前已被专用模型涵盖。
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
我们表明,如果基于深度学习的插值器使用球形线性插值器作为基线,可以更准确,有效地求解在一组关键帧上进行人类运动的任务。我们从经验上证明了我们在实现最新性能的公开数据集上的方法的实力。我们通过证明$ \ delta $ - 优势相对于最后已知帧(也称为零速度模型)的参考,进一步概括了这些结果。这支持了一个更一般的结论,即在参考框架本地对输入帧的工作比以前的工作中主张的全球(世界)参考框架更准确,更强大。我们的代码可在https://github.com/boreshkinai/delta-interpolator上公开获取。
translated by 谷歌翻译
我们解决了从文本描述中产生不同3D人类动作的问题。这项具有挑战性的任务需要两种方式的联合建模:从文本中理解和提取有用的人类以人为中心的信息,然后产生人类姿势的合理和现实序列。与大多数以前的工作相反,该作品着重于从文本描述中产生单一的,确定性的动作,我们设计了一种可以产生多种人类动作的变异方法。我们提出了Temos,这是一种具有人体运动数据的变异自动编码器(VAE)训练的文本生成模型,并结合了与VAE潜在空间兼容的文本编码器结合使用的文本编码器。我们显示Temos框架可以像先前的工作一样产生基于骨架的动画,以及更具表现力的SMPL身体运动。我们在套件运动语言基准上评估了我们的方法,尽管相对简单,但对艺术的状态表现出显着改善。代码和模型可在我们的网页上找到。
translated by 谷歌翻译
用全球性结构(例如编织)合成人体运动是一个具有挑战性的任务。现有方法倾向于集中在局部光滑的姿势过渡并忽视全球背景或运动的主题。在这项工作中,我们提出了一种音乐驱动的运动综合框架,其产生与输入节拍同步的人类运动的长期序列,并共同形成尊重特定舞蹈类型的全局结构。此外,我们的框架可以实现由音乐内容控制的不同运动,而不仅仅是由节拍。我们的音乐驱动舞蹈综合框架是一个分层系统,包括三个层次:姿势,图案和编排。姿势水平由LSTM组件组成,该组件产生时间相干的姿势。图案级别引导一组连续姿势,形成一个使用新颖运动感知损失所属的特定分布的运动。并且舞蹈级别选择所执行的运动的顺序,并驱动系统遵循舞蹈类型的全球结构。我们的结果展示了我们的音乐驱动框架的有效性,以在各种舞蹈类型上产生自然和一致的运动,控制合成运动的内容,并尊重舞蹈的整体结构。
translated by 谷歌翻译
神经网络的出现彻底改变了运动合成领域。然而,学会从给定的分布中无条件合成动作仍然是一项具有挑战性的任务,尤其是当动作高度多样化时。我们提出了Modi,这是一种无条件的生成模型,可以合成各种动作。我们的模型在完全无监督的环境中训练,从多样化,非结构化和未标记的运动数据集中进行了训练,并产生了一个行为良好,高度语义的潜在空间。我们的模型的设计遵循StyleGAN的多产架构,并将其两个关键技术组件调整为运动域:一组样式编码,这些样式编码注入了生成器层次结构的每个级别和映射功能,并形成了一个学习和形成一个分离的潜在空间。我们表明,尽管数据集中缺乏任何结构,但潜在空间可以在语义上聚集,并促进语义编辑和运动插值。此外,我们提出了一种将未见动作转向潜在空间的技术,并展示了基于潜在的运动编辑操作,否则这些动作无法通过天真地操纵明确的运动表示无法实现。我们的定性和定量实验表明,我们的框架达到了最新的合成质量,可以遵循高度多样化的运动数据集的分布。代码和训练有素的模型将在https://sigal-raab.github.io/modi上发布。
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
在本文中,我们为音乐驱动的舞蹈运动综合构成了一个新颖的框架,并具有可控的关键姿势约束。与仅基于音乐生成舞蹈运动序列的方法相反,该工作的目标是综合由音乐驱动的高质量舞蹈运动以及用户执行的定制姿势。我们的模型涉及两个用于音乐和运动表示形式的单模式变压器编码器,以及用于舞蹈动作生成的跨模式变压器解码器。跨模式变压器解码器可以通过引入局部邻居位置嵌入来使其合成平滑舞蹈运动序列合成平滑舞蹈运动序列的能力。这种机制使解码器对关键姿势和相应位置更加敏感。我们的舞蹈合成模型通过广泛的实验在定量和定性评估上取得了令人满意的表现,这证明了我们提出的方法的有效性。
translated by 谷歌翻译
扩散概率模型(DPM)由于其有希望的结果和对跨模式合成的支持,已成为有条件产生的流行方法。条件合成中的一个关键逃亡者是在条件输入和生成的输出之间实现高对应。大多数现有方法通过将先验纳入变异下限中,隐含地学习了这种关系。在这项工作中,我们采用了另一条路线 - 我们通过使用对比度学习来最大化其共同信息来增强输入输出连接。为此,我们引入了有条件的离散对比扩散(CDCD)损失,并设计了两种对比扩散机制,以有效地将其纳入剥离过程中。我们通过将CDCD与传统的变分目标联系起来来制定CDCD。我们证明了我们的方法在三种多种多样的条件合成任务中的评估中的功效:舞蹈到音乐的生成,文本到图像综合和班级调节图像综合。在每个方面,我们达到最新的或更高的合成质量并提高输入输出对应关系。此外,提出的方法改善了扩散模型的收敛性,将所需扩散步骤的数量减少了两个基准的35%以上,从而大大提高了推理速度。
translated by 谷歌翻译
我们提出了一个基于神经网络的系统,用于长期,多动能人类运动合成。该系统被称为神经木偶,可以从简单的用户输入中平稳过渡,包括带有预期动作持续时间的动作标签,以及如果用户指定的话,则可以产生高质量和有意义的动作。我们系统的核心是一种基于变压器的新型运动生成模型,即Marionet,它可以在给定的动作标签给定不同的动作。与现有运动生成模型不同,Marionet利用了过去的运动剪辑和未来动作标签的上下文信息,专门用于生成可以平稳融合历史和未来动作的动作。具体而言,Marionet首先将目标动作标签和上下文信息编码为动作级潜在代码。该代码通过时间展开模块将代码展开为帧级控制信号,然后可以将其与其他帧级控制信号(如目标轨迹)结合使用。然后以自动回归方式生成运动帧。通过依次应用木偶,系统神经木偶可以借助两个简单的方案(即“影子开始”和“动作修订”)来稳健地产生长期的多动作运动。与新型系统一起,我们还提供了一个专门针对多动运动综合任务的新数据集,其中包含动作标签及其上下文信息。进行了广泛的实验,以研究我们系统产生的动作的动作准确性,自然主义和过渡平滑度。
translated by 谷歌翻译
Recent CLIP-guided 3D optimization methods, e.g., DreamFields and PureCLIPNeRF achieve great success in zero-shot text-guided 3D synthesis. However, due to the scratch training and random initialization without any prior knowledge, these methods usually fail to generate accurate and faithful 3D structures that conform to the corresponding text. In this paper, we make the first attempt to introduce the explicit 3D shape prior to CLIP-guided 3D optimization methods. Specifically, we first generate a high-quality 3D shape from input texts in the text-to-shape stage as the 3D shape prior. We then utilize it as the initialization of a neural radiance field and then optimize it with the full prompt. For the text-to-shape generation, we present a simple yet effective approach that directly bridges the text and image modalities with a powerful text-to-image diffusion model. To narrow the style domain gap between images synthesized by the text-to-image model and shape renderings used to train the image-to-shape generator, we further propose to jointly optimize a learnable text prompt and fine-tune the text-to-image diffusion model for rendering-style image generation. Our method, namely, Dream3D, is capable of generating imaginative 3D content with better visual quality and shape accuracy than state-of-the-art 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
最近,GaN反演方法与对比语言 - 图像预先绘制(CLIP)相结合,可以通过文本提示引导零拍摄图像操作。然而,由于GaN反转能力有限,它们对不同实物的不同实物的应用仍然困难。具体地,这些方法通常在与训练数据相比,改变对象标识或产生不需要的图像伪影的比较与新颖姿势,视图和高度可变内容重建具有新颖姿势,视图和高度可变内容的困难。为了减轻这些问题并实现真实图像的忠实操纵,我们提出了一种新的方法,Dumbused Clip,其使用扩散模型执行文本驱动的图像操纵。基于近期扩散模型的完整反转能力和高质量的图像生成功率,即使在看不见的域之间也成功地执行零拍摄图像操作。此外,我们提出了一种新颖的噪声组合方法,允许简单的多属性操作。与现有基线相比,广泛的实验和人类评估确认了我们的方法的稳健和卓越的操纵性能。
translated by 谷歌翻译
现有的基于密钥帧的运动合成主要集中于循环动作或短期运动的产生,例如步行,跑步和近距离姿势之间的过渡。但是,这些方法将在处理复杂和即兴运动时,例如舞蹈表演和武术时会大大降低合成运动的自然性和多样性。此外,当前的研究缺乏对生成的运动的细粒度控制,这对于智能的人类计算机互动和动画创作至关重要。在本文中,我们提出了一个基于多个约束的新型基于关键的运动生成网络,该网络可以通过学习的知识来实现​​多样化的舞蹈综合。具体而言,该算法主要基于复发性神经网络(RNN)和变压器体系结构制定。我们网络的骨干是由两个长期记忆(LSTM)单元组成的层次RNN模块,其中第一个LSTM用于将历史框架的姿势信息嵌入潜在空间中,第二个LSTM用于使用第二个LSTM,并且使用了第二个LSTM。预测下一帧的人类姿势。此外,我们的框架包含两个基于变压器的控制器,这些控制器分别用于建模根轨迹和速度因子的约束,以更好地利用框架的时间上下文并实现细粒度的运动控制。我们在包含各种现代舞蹈的舞蹈数据集上验证了拟议的方法。三个定量分析的结果验证了我们算法的优势。视频和定性实验结果表明,我们算法产生的复杂运动序列即使是长期合成,也可以在关键帧之间实现多种和平滑的运动过渡。
translated by 谷歌翻译
Achieving multiple genres and long-term choreography sequences from given music is a challenging task, due to the lack of a multi-genre dataset. To tackle this problem,we propose a Multi Art Genre Intelligent Choreography Dataset (MagicDance). The data of MagicDance is captured from professional dancers assisted by motion capture technicians. It has a total of 8 hours 3D motioncapture human dances with paired music, and 16 different dance genres. To the best of our knowledge, MagicDance is the 3D dance dataset with the most genres. In addition, we find that the existing two types of methods (generation-based method and synthesis-based method) can only satisfy one of the diversity and duration, but they can complement to some extent. Based on this observation, we also propose a generation-synthesis choreography network (MagicNet), which cascades a Diffusion-based 3D Diverse Dance fragments Generation Network (3DGNet) and a Genre&Coherent aware Retrieval Module (GCRM). The former can generate various dance fragments from only one music clip. The latter is utilized to select the best dance fragment generated by 3DGNet and switch them into a complete dance according to the genre and coherent matching score. Quantitative and qualitative experiments demonstrate the quality of MagicDance, and the state-of-the-art performance of MagicNet.
translated by 谷歌翻译