Heritage · 2021 · 58 citations · 35 references
ArchitectureDesign3D ModelingAugmented Reality DesignVirtual Reality Design3D AnimationAnimationAugmented RealityMotion CaptureVirtual Environment DesignVirtual RealityAnimation For Virtual RealityAugmented Reality PrototypingDigital Human ModelingHuman-avatar InteractionMorphingMotion Capture AvatarsPhysical Interaction With The EnvironmentVirtual Avatars
Virtual Humans are increasingly used in interactive Virtual Cultural Heritage presentations, yet creating realistic ones has traditionally required costly motion‑capture studios and extensive 3D animation resources. This study presents a workflow to align and fine‑tune Virtual Humans’ appearance to their roles and affective components, leveraging wearable mocap and software advances. The workflow starts with motion capture and segmentation, then retargets and animates avatars with lip sync and face morphing, and is validated in VR at the Mastic Museum of Chios and on‑site via AR. Formative evaluation confirms the hypothesis and yields guidelines for replicating the workflow.
Virtual Humans are becoming a commodity in computing technology and lately have been utilized in the context of interactive presentations in Virtual Cultural Heritage environments and exhibitions. To this end, this research work underlines the importance of aligning and fine-tuning Virtual Humans’ appearance to their roles and highlights the importance of affective components. Building realistic Virtual Humans was traditionally a great challenge requiring a professional motion capturing studio and heavy resources in 3D animation and design. In this paper, a workflow for their implementation is presented, based on current technological trends in wearable mocap systems and advancements in software technology for their implementation, animation, and visualization. The workflow starts from motion recording and segmentation to avatar implementation, retargeting, animation, lip synchronization, face morphing, and integration to a virtual or physical environment. The testing of the workflow occurs in a use case for the Mastic Museum of Chios and the implementation is validated both in a 3D virtual environment accessed through Virtual Reality and on-site at the museum through an Augmented Reality application. The findings, support the initial hypothesis through a formative evaluation, and lessons learned are transformed into a set of guidelines to support the replication of this work.
35
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
Zhe Cao, Tomas Simon, Shih-En Wei et al. · 2017 · 7.3K citations
Real-time human pose recognition in parts from single depth images
Jamie Shotton, Andrew Fitzgibbon, Mat Cook et al. · 2011 · 3.5K citations
Vergence–accommodation conflicts hinder visual performance and cause visual fatigue
David M. Hoffman, Ahna R. Girshick, Kurt Akeley et al. · Journal of Vision · 2008 · 1.6K citations · Full text
Dushyant Mehta, Srinath Sridhar, Oleksandr Sotnychenko et al. · ACM Transactions on Graphics · 2017 · 1.2K citations · Full text