Tomorrow’s digital ‘human’ creation will be based on AI learning from authentic real-world data of people recorded physically in action with the utmost 3D fidelity.
The hand at a straight neutral posture was scanned using the 3dMDhand system. Next, the hand was scanned while in a power grip at each of three wrist postures (20° of radial deviation, neutral, and 30° of ulnar deviation), along with the corresponding palmar hand cast.
We collected a large dataset comprising of textured 3D hand scans. Our hand data were captured during a special exhibition at the Science Museum, London. The capturing apparatus utilized for this task was a 3dMDhand5 system, which is an active stereo photogrammetry software-driven optics-based system, which produces high quality dense meshes.
Introducing ARCTIC – the first dataset of free-form interactions of hands and articulated objects. ARCTIC has 1.2M images paired with accurate 3D meshes for both hands and for objects that move and deform over time. The dataset also provides hand-object contact information.
It is concluded that the proposed posture correction approach can effectively improve the accuracy of the hand SSM and therefore enables its wide usage in human-integrated digital twin applications.
3dMDbody Capture at the Science Museum, London
Date: June 2019. Source: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA. Proceedings Page(s): 10967-10977. Abstract: To facilitate the analysis of human actions, interactions and emotions, we compute a 3D model of human body pose, hand pose, and facial expression from a single monocular image. To achieve this, we…