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
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
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
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
本文介绍了一个新型的预训练的空间时间多对一(p-STMO)模型,用于2D到3D人类姿势估计任务。为了减少捕获空间和时间信息的困难,我们将此任务分为两个阶段:预训练(I期)和微调(II阶段)。在第一阶段,提出了一个自我监督的预训练子任务,称为蒙面姿势建模。输入序列中的人关节在空间和时间域中随机掩盖。利用denoising自动编码器的一般形式以恢复原始的2D姿势,并且编码器能够以这种方式捕获空间和时间依赖性。在第二阶段,将预训练的编码器加载到STMO模型并进行微调。编码器之后是一个多对一的框架聚合器,以预测当前帧中的3D姿势。尤其是,MLP块被用作STMO中的空间特征提取器,其性能比其他方法更好。此外,提出了一种时间下采样策略,以减少数据冗余。在两个基准上进行的广泛实验表明,我们的方法优于较少参数和较少计算开销的最先进方法。例如,我们的P-STMO模型在使用CPN作为输入的2D姿势时,在Human3.6M数据集上达到42.1mm MPJPE。同时,它为最新方法带来了1.5-7.1倍的速度。代码可在https://github.com/patrick-swk/p-stmo上找到。
translated by 谷歌翻译
Learning 3D human pose prior is essential to human-centered AI. Here, we present GFPose, a versatile framework to model plausible 3D human poses for various applications. At the core of GFPose is a time-dependent score network, which estimates the gradient on each body joint and progressively denoises the perturbed 3D human pose to match a given task specification. During the denoising process, GFPose implicitly incorporates pose priors in gradients and unifies various discriminative and generative tasks in an elegant framework. Despite the simplicity, GFPose demonstrates great potential in several downstream tasks. Our experiments empirically show that 1) as a multi-hypothesis pose estimator, GFPose outperforms existing SOTAs by 20% on Human3.6M dataset. 2) as a single-hypothesis pose estimator, GFPose achieves comparable results to deterministic SOTAs, even with a vanilla backbone. 3) GFPose is able to produce diverse and realistic samples in pose denoising, completion and generation tasks. Project page https://sites.google.com/view/gfpose/
translated by 谷歌翻译
估计单眼视频的3D人类姿势是由于深度模糊和自动阻塞的具有挑战性的任务。大多数现有的作品试图通过利用空间和时间关系来解决这两个问题。然而,这些作品忽略了它是存在多种可行解决方案(即假设)的逆问题。为了减轻这种限制,我们提出了一种多假设变压器(MHFormer),其学习多个合理的姿势假设的时空表示。为了有效地模拟多假设依赖性并构建跨假设特征的强烈关系,任务分解为三个阶段:(i)生成多个初始假设表示; (ii)模型自立通信,将多个假设合并到单个融合表示中,然后将其分组成几个分歧假设; (iii)学习横向假设通信并汇总多假设特征以合成最终的3D姿势。通过上述过程,最终表示增强,合成的姿势更准确。广泛的实验表明,MHFORMER在两个具有挑战性的数据集上实现最先进的结果:Humanet3.6M和MPI-INF-3DHP。没有钟声和吹口哨,其性能超过了以人3.6M的大幅度为3%的最佳结果。代码和模型可在https://github.com/vegetebird/mhformer中找到。
translated by 谷歌翻译
Estimating 3D human motion from an egocentric video sequence is critical to human behavior understanding and applications in VR/AR. However, naively learning a mapping between egocentric videos and human motions is challenging, because the user's body is often unobserved by the front-facing camera placed on the head of the user. In addition, collecting large-scale, high-quality datasets with paired egocentric videos and 3D human motions requires accurate motion capture devices, which often limit the variety of scenes in the videos to lab-like environments. To eliminate the need for paired egocentric video and human motions, we propose a new method, Ego-Body Pose Estimation via Ego-Head Pose Estimation (EgoEgo), that decomposes the problem into two stages, connected by the head motion as an intermediate representation. EgoEgo first integrates SLAM and a learning approach to estimate accurate head motion. Then, taking the estimated head pose as input, it leverages conditional diffusion to generate multiple plausible full-body motions. This disentanglement of head and body pose eliminates the need for training datasets with paired egocentric videos and 3D human motion, enabling us to leverage large-scale egocentric video datasets and motion capture datasets separately. Moreover, for systematic benchmarking, we develop a synthetic dataset, AMASS-Replica-Ego-Syn (ARES), with paired egocentric videos and human motion. On both ARES and real data, our EgoEgo model performs significantly better than the state-of-the-art.
translated by 谷歌翻译
现代的多层感知器(MLP)模型在不自我注意力的情况下学习视觉表现方面显示了竞争成果。但是,现有的MLP模型不擅长捕获本地细节,并且缺乏人类配置的先验知识,这限制了其骨骼表示学习的模型能力。为了解决这些问题,我们提出了一个名为GraphMLP的简单而有效的图形增强的MLP样结构,该体系结构将MLP和图形卷积网络(GCN)组合在3D人类姿势估计的全球 - 局部 - 单位图形统一体系中。GraphMLP将人体的图结构结合到MLP模型中,以满足域特异性需求,同时允许局部和全局空间相互作用。广泛的实验表明,所提出的GraphMLP在两个数据集(即Human3.6M和MPI-INF-3DHP)上实现了最先进的性能。我们的源代码和预估计的模型将公开可用。
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
单眼3D人姿势估计技术有可能大大增加人类运动数据的可用性。单位图2D-3D提升使用图卷积网络(GCN)的表现最佳模型,通常需要一些手动输入来定义不同的身体关节之间的关系。我们提出了一种基于变压器的新型方法,该方法使用更广泛的自我发场机制来学习代表关节的代币序列。我们发现,使用中间监督以及堆叠编码器福利性能之间的剩余连接。我们还建议,将错误预测作为多任务学习框架的一部分,可以通过允许网络弥补其置信度来改善性能。我们进行广泛的消融研究,以表明我们的每项贡献都会提高性能。此外,我们表明我们的方法的表现超过了最新的单帧3D人类姿势估计的最新技术状态。我们的代码和训练有素的模型可在GitHub上公开提供。
translated by 谷歌翻译
尽管近年来,在无单眼制造商的人类运动捕获上取得了重大进展,但最先进的方法仍然很难在遮挡场景中获得令人满意的结果。有两个主要原因:一个是遮挡的运动捕获本质上是模棱两可的,因为各种3D姿势可以映射到相同的2D观测值,这总是导致不可靠的估计。另一个是没有足够的封闭人类数据可用于训练健壮的模型。为了解决这些障碍,我们的钥匙界是使用非封闭式人类数据来学习以自我监督策略的封闭人类的联合时空运动。为了进一步减少合成数据和实际遮挡数据之间的差距,我们构建了第一个3D遮挡运动数据集〜(Ocmotion),可用于训练和测试。我们在2D地图中编码运动,并在非封闭数据上合成遮挡,以进行自我监督训练。然后,设计空间层层以学习联合级别的相关性。博学的先前降低了闭塞的歧义,并且对各种遮挡类型具有坚固态度,然后采用这些类型来帮助封闭的人类运动捕获。实验结果表明,我们的方法可以从具有良好概括能力和运行时效率的遮挡视频中产生准确且相干的人类动作。数据集和代码可在\ url {https://github.com/boycehbz/chomp}上公开获得。
translated by 谷歌翻译
尽管来自视频的3D人类姿势估算的巨大进展,但是充分利用冗余2D姿势序列来学习用于生成一个3D姿势的代表表示的开放问题。为此,我们提出了一种改进的基于变压器的架构,称为冲压变压器,简单地有效地将长期的2D联合位置升高到单个3D姿势。具体地,采用Vanilla变压器编码器(VTE)来模拟2D姿势序列的远程依赖性。为了减少序列的冗余,vte的前馈网络中的完全连接的层被冲击卷积替换,以逐步缩小序列长度并从本地上下文聚合信息。修改的VTE称为STRIVEIVERCHER ENCODER(STE),其构建在VTE的输出时。 STE不仅有效地将远程信息聚集到分层全球和本地时尚的单载体表示,而且显着降低了计算成本。此外,全序列和单个目标帧尺度都设计了全序,分别适用于VTE和ST的输出。该方案与单个目标帧监督结合施加额外的时间平滑度约束,因此有助于产生更平滑和更准确的3D姿势。所提出的轮廓变压器在两个具有挑战性的基准数据集,Human3.6M和HumanVa-I中进行评估,并通过更少的参数实现最先进的结果。代码和模型可用于\ url {https://github.com/vegetebird/stridedtransformer-pose3d}。
translated by 谷歌翻译
视频3D人类姿势估计旨在将视频中人类关节的3D坐标定位。最近的基于变压器的方法着重于从顺序2D姿势捕获时空信息,由于在2D姿势估计的步骤中丢失了视觉深度特征,因此无法有效地对上下文深度特征进行建模。在本文中,我们将范式简化为端到端框架,实例引导的视频变压器(IVT),该范式可以有效地从视觉特征中学习时空的上下文深度信息,并直接从视频框架中预测3D姿势。特别是,我们首先将视频框架作为一系列实例引导令牌,每个令牌都可以预测人类实例的3D姿势。这些令牌包含身体结构信息,因为它们是由关节偏移从人体中心到相应身体关节的指导提取的。然后,这些令牌被发送到IVT中,以学习时空的上下文深度。此外,我们提出了一种跨尺度实例引导的注意机制,以处理多个人之间的变异量表。最后,每个人的3D姿势都是通过坐标回归从实例引导的代币中解码的。在三个广泛使用的3D姿势估计基准上进行的实验表明,拟议的IVT实现了最先进的性能。
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
We propose the first joint audio-video generation framework that brings engaging watching and listening experiences simultaneously, towards high-quality realistic videos. To generate joint audio-video pairs, we propose a novel Multi-Modal Diffusion model (i.e., MM-Diffusion), with two-coupled denoising autoencoders. In contrast to existing single-modal diffusion models, MM-Diffusion consists of a sequential multi-modal U-Net for a joint denoising process by design. Two subnets for audio and video learn to gradually generate aligned audio-video pairs from Gaussian noises. To ensure semantic consistency across modalities, we propose a novel random-shift based attention block bridging over the two subnets, which enables efficient cross-modal alignment, and thus reinforces the audio-video fidelity for each other. Extensive experiments show superior results in unconditional audio-video generation, and zero-shot conditional tasks (e.g., video-to-audio). In particular, we achieve the best FVD and FAD on Landscape and AIST++ dancing datasets. Turing tests of 10k votes further demonstrate dominant preferences for our model. The code and pre-trained models can be downloaded at https://github.com/researchmm/MM-Diffusion.
translated by 谷歌翻译
最近的2D-3D人类姿势估计工作倾向于利用人体骨架的拓扑形成的图形结构。但是,我们认为这种骨架拓扑太稀疏,无法反映身体结构并遭受严重的2D-3D模糊问题。为了克服这些弱点,我们提出了一种新颖的图表卷积网络架构,层次图形网络(HGN)。它基于我们的多尺度图结构建筑策略产生的密度图形拓扑,从而提供更精细的几何信息。所提出的架构包含三个并行组织的稀疏微小表示子网,其中通过新颖的特征融合策略处理多尺度图形结构特征,并通过新颖的特征融合策略进行交换信息,导致丰富的分层表示。我们还介绍了3D粗网格约束,以进一步提高与细节相关的特征学习。广泛的实验表明,我们的HGN通过减少的网络参数实现了最先进的性能
translated by 谷歌翻译
在深度学习的时代,具有未知校准未知校准的多个摄像机的人类姿态估计几乎没有关注迄今为止。我们展示如何培训一个神经模型,以高精度和最小延迟开销来执行此任务。由于多视图闭塞,所提出的模型考虑了联合位置不确定性,并且只需要2D关键点数据进行培训。我们的方法优于良好的人机3.6M数据集上的经典捆绑调整和弱监督单眼3D基线,以及野外滑雪姿势PTZ数据集的更具挑战性。
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
本文提出了一个简单的基线框架,用于基于视频的2D/3D人姿势估计,该估计可以比现有作品实现10倍提高效率,而无需任何性能降级,名为Deciwatch。与当前在视频中估算每个帧的解决方案不同,Deciwatch引入了一个简单而有效的样品探测框架框架,该框架只能通过人类动作的连续性和轻巧的姿势表示,仅观看稀疏采样的框架。具体而言,DeciWatch均匀地示例少于10%的视频帧以进行详细估计,以有效的变压器体系结构来确定估计的2D/3D姿势,然后使用另一个基于变压器的网络准确地恢复其余帧。通过四个数据集的三个基于视频的人姿势估计和身体网格恢复任务的全面实验结果验证了Deciwatch的效率和有效性。代码可在https://github.com/cure-lab/deciwatch上找到。
translated by 谷歌翻译