CIRCLE: Capture In Rich Contextual Environments
CIRCLE: Capture In Rich Contextual Environments
复制标题
DOI：
10.1109/cvpr52729.2023.02032
复制
发表时间：
2023-03
期刊：
影响因子：
--
通讯作者：
Joao Pedro Araujo;Jiaman Li;Karthik Vetrivel;Rishi G. Agarwal;D. Gopinath;Jiajun Wu;Alexander Clegg;C. Liu
中科院分区：
文献类型：
--
作者：
Joao Pedro Araujo;Jiaman Li;Karthik Vetrivel;Rishi G. Agarwal;D. Gopinath;Jiajun Wu;Alexander Clegg;C. Liu
在上下文的生态环境中综合3D人类运动对于模拟人们在现实世界中执行的现实活动很重要。但是，常规的基于光学的运动捕获系统不适合同时捕获人类运动和复杂场景。缺乏丰富的上下文3D人类运动数据集为创建高质量生成的人类运动模型提供了障碍。我们提出了一个新颖的运动采集系统，在该系统中，演员在一个高度背景的虚拟世界中感知并在现实世界中被捕获的运动。我们的系统可以在高度多样化的场景中快速收集高质量的人类运动，而无需遮挡或需要在现实世界中进行物理场景建设。我们提出了一个圆圈，这是一个数据集，其中包含10个小时的全身，从9个场景中从5个主题中进行运动，并与以各种形式表示的环境中以自我为中心的信息，例如RGBD视频。我们使用此数据集来训练一个在场景信息上生成人类运动的模型。利用我们的数据集，该模型学会使用以自我为中心的场景信息在复杂的3D场景的背景下实现非平凡的到达任务。要下载数据，请访问我们的网站。
Synthesizing 3D human motion in a contextual, ecological environment is important for simulating realistic activities people perform in the real world. However, conventional optics-based motion capture systems are not suited for simultaneously capturing human movements and complex scenes. The lack of rich contextual 3D human motion datasets presents a roadblock to creating high-quality generative human motion models. We propose a novel motion acquisition system in which the actor perceives and operates in a highly contextual virtual world while being motion captured in the real world. Our system enables rapid collection of high-quality human motion in highly diverse scenes, without the concern of occlusion or the need for physical scene construction in the real world. We present CIRCLE, a dataset containing 10 hours of full-body reaching motion from 5 subjects across nine scenes, paired with ego-centric information of the environment represented in various forms, such as RGBD videos. We use this dataset to train a model that generates human motion conditioned on scene information. Leveraging our dataset, the model learns to use ego-centric scene information to achieve non-trivial reaching tasks in the context of complex 3D scenes. To download the data please visit our website.