Can we make virtual characters in a scene interact with their surrounding objects through simple instructions? Is it possible to synthesize such motion plausibly with a diverse set of objects and instructions? Inspired by these questions, we present the first framework to synthesize the full-body motion of virtual human characters performing specified actions with 3D objects placed within their reach. Our system takes as input textual instructions specifying the objects and the associated intentions of the virtual characters and outputs diverse sequences of full-body motions. This is in contrast to existing work, where full-body action synthesis methods generally do not consider object interactions, and human-object interaction methods focus mainly on synthesizing hand or finger movements for grasping objects. We accomplish our objective by designing an intent-driven full-body motion generator, which uses a pair of decoupled conditional variational autoencoders (CVAE) to learn the motion of the body parts in an autoregressive manner. We also optimize for the positions of the objects with six degrees of freedom (6DoF) such that they plausibly fit within the hands of the synthesized characters. We compare our proposed method with the existing methods of motion synthesis and establish a new and stronger state-of-the-art for the task of intent-driven motion synthesis. Through a user study, we further show that our synthesized full-body motions appear more realistic to the participants in more than 80% of scenarios compared to the current state-of-the-art methods, and are perceived to be as good as the ground truth on several occasions.
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
3D reconstruction and novel view synthesis of dynamic scenes from collections of single views recently gained increased attention. Existing work shows impressive results for synthetic setups and forward-facing real-world data, but is severely limited in the training speed and angular range for generating novel views. This paper addresses these limitations and proposes a new method for full 360{\deg} novel view synthesis of non-rigidly deforming scenes. At the core of our method are: 1) An efficient deformation module that decouples the processing of spatial and temporal information for acceleration at training and inference time; and 2) A static module representing the canonical scene as a fast hash-encoded neural radiance field. We evaluate the proposed approach on the established synthetic D-NeRF benchmark, that enables efficient reconstruction from a single monocular view per time-frame randomly sampled from a full hemisphere. We refer to this form of inputs as monocularized data. To prove its practicality for real-world scenarios, we recorded twelve challenging sequences with human actors by sampling single frames from a synchronized multi-view rig. In both cases, our method is trained significantly faster than previous methods (minutes instead of days) while achieving higher visual accuracy for generated novel views. Our source code and data is available at our project page https://graphics.tu-bs.de/publications/kappel2022fast.
translated by 谷歌翻译
从单眼RGB图像中捕获的3D人类运动捕获符合受试者与复杂且可能可变形的环境的相互作用的相互作用是一个非常具有挑战性,不足和探索不足的问题。现有方法仅薄弱地解决它,并且当人类与场景表面互动时,通常不会建模可能发生的表面变形。相比之下,本文提出了mocapdeform,即单眼3D人体运动捕获的新框架,该框架是第一个明确模拟3D场景的非刚性变形,以改善3D人体姿势估计和可变形环境的重建。 Mocapdeform接受单眼RGB视频,并在相机空间中对齐一个3D场景。它首先使用基于新的射线广播的策略将输入单眼视频中的主题以及密集的触点标签进行定位。接下来,我们的人类环境相互作用约束被利用以共同优化全局3D人类姿势和非刚性表面变形。 Mocapdeform比在几个数据集上的竞争方法获得了更高的精度,包括我们新记录的具有变形背景场景的方法。
translated by 谷歌翻译
我们提出Unrealego,即,一种用于以Egentric 3D人类姿势估计的新的大规模自然主义数据集。Unrealego是基于配备两个鱼眼摄像机的眼镜的高级概念,可用于无约束的环境。我们设计了它们的虚拟原型,并将其附加到3D人体模型中以进行立体视图捕获。接下来,我们会产生大量的人类动作。结果,Unrealego是第一个在现有的EgeCentric数据集中提供最大动作的野外立体声图像的数据集。此外,我们提出了一种新的基准方法,其简单但有效的想法是为立体声输入设计2D关键点估计模块,以改善3D人体姿势估计。广泛的实验表明,我们的方法在定性和定量上优于先前的最新方法。Unrealego和我们的源代码可在我们的项目网页上找到。
translated by 谷歌翻译
到目前为止,已经研究了基于学习坐标的体积3D场景表示,例如神经辐射场(NERF),假设RGB或RGB-D图像是输入。同时,从神经科学文献中知道,人类视觉系统(HVS)的定制是为了处理异步亮度而不是同步的RGB图像,以构建和不断更新周围环境的心理3D表示,以进行导航和生存。受HVS原理启发的视觉传感器是事件摄像机。因此,事件是稀疏和异步的每个像素亮度(或颜色通道)更改信号。与神经3D场景表示学习的现有作品相反,本文从新的角度解决了问题。我们证明,可以从异步事件流中学习适用于RGB空间中新型视图合成的NERF。我们的模型在RGB空间中具有挑战性场景的新颖的视野具有很高的视觉准确性,即使它们的数据训练得多(即,来自单个事件摄像机的事件流围绕对象移动)并更有效(由于其效率更高(由于其培训)(由于事件流的固有稀疏性)比现有的NERF模型接受了RGB图像。我们将发布我们的数据集和源代码,请参见https://4dqv.mpi-inf.mpg.de/eventnerf/。
translated by 谷歌翻译
捕获一般的变形场景对于许多计算机图形和视觉应用至关重要,当只有单眼RGB视频可用时,这尤其具有挑战性。竞争方法假设密集的点轨道,3D模板,大规模训练数据集或仅捕获小规模的变形。与这些相反,我们的方法UB4D在挑战性的情况下超过了先前的艺术状态,而没有做出这些假设。我们的技术包括两个新的,在非刚性3D重建的背景下,组件,即1)1)针对非刚性场景的基于坐标的和隐性的神经表示,这使动态场景无偏重建,2)新颖的新颖。动态场景流量损失,可以重建较大的变形。我们的新数据集(将公开可用)的结果表明,就表面重建精度和对大变形的鲁棒性而言,对最新技术的明显改善。访问项目页面https://4dqv.mpi-inf.mpg.de/ub4d/。
translated by 谷歌翻译
无标记的单眼3D人类运动捕获(MOCAP)与场景相互作用是一个充满挑战的研究主题,与扩展现实,机器人技术和虚拟头像生成有关。由于单眼环境的固有深度歧义,使用现有方法捕获的3D运动通常包含严重的人工制品,例如不正确的身体场景互穿,抖动和身体漂浮。为了解决这些问题,我们提出了HULC,这是一种新的3D人类MOCAP方法,它知道场景几何形状。 HULC估计3D姿势和密集的身体环境表面接触,以改善3D定位以及受试者的绝对尺度。此外,我们基于新的姿势歧管采样,引入了3D姿势轨迹优化,该采样解决了错误的身体环境互穿。尽管所提出的方法与现有场景感知的单眼MOCAP算法相比需要较少的结构化输入,但它会产生更加可行的姿势:HULC显着且一致地在各种实验和不同指标上都优于现有方法。项目页面:https://vcai.mpi-inf.mpg.de/projects/hulc/。
translated by 谷歌翻译
照片中的户外场景的照片拟实的编辑需要对图像形成过程的深刻理解和场景几何,反射和照明的准确估计。然后可以在保持场景Albedo和几何形状的同时进行照明的微妙操纵。我们呈现NERF-OSR,即,基于神经辐射场的户外场景复兴的第一种方法。与现有技术相比,我们的技术允许仅使用在不受控制的设置中拍摄的户外照片集合的场景照明和相机视点。此外,它能够直接控制通过球面谐波模型所定义的场景照明。它还包括用于阴影再现的专用网络,这对于高质量的室外场景致密至关重要。为了评估所提出的方法,我们收集了几个户外站点的新基准数据集,其中每个站点从多个视点拍摄和不同的时间。对于每个定时,360度环境映射与颜色校准Chequerboard一起捕获,以允许对实际真实的真实数据进行准确的数值评估。反对本领域的状态的比较表明,NERF-OSR能够以更高的质量和逼真的自阴影再现来实现可控的照明和视点编辑。我们的方法和数据集将在https://4dqv.mpi-inf.mpg.de/nerf-OSR/上公开可用。
translated by 谷歌翻译
综合照片 - 现实图像和视频是计算机图形的核心,并且是几十年的研究焦点。传统上,使用渲染算法(如光栅化或射线跟踪)生成场景的合成图像,其将几何形状和材料属性的表示为输入。统称,这些输入定义了实际场景和呈现的内容,并且被称为场景表示(其中场景由一个或多个对象组成)。示例场景表示是具有附带纹理的三角形网格(例如,由艺术家创建),点云(例如,来自深度传感器),体积网格(例如,来自CT扫描)或隐式曲面函数(例如,截短的符号距离)字段)。使用可分辨率渲染损耗的观察结果的这种场景表示的重建被称为逆图形或反向渲染。神经渲染密切相关,并将思想与经典计算机图形和机器学习中的思想相结合,以创建用于合成来自真实观察图像的图像的算法。神经渲染是朝向合成照片现实图像和视频内容的目标的跨越。近年来,我们通过数百个出版物显示了这一领域的巨大进展,这些出版物显示了将被动组件注入渲染管道的不同方式。这种最先进的神经渲染进步的报告侧重于将经典渲染原则与学习的3D场景表示结合的方法,通常现在被称为神经场景表示。这些方法的一个关键优势在于它们是通过设计的3D-一致,使诸如新颖的视点合成捕获场景的应用。除了处理静态场景的方法外,我们还涵盖了用于建模非刚性变形对象的神经场景表示...
translated by 谷歌翻译