Controllable face editing for video reconstruction in human digital twins

Lin, Chengde; Xiong, Shengwu

doi:10.1016/j.imavis.2022.104517

Cited by 6 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al [74] developed a novel 3D face modeling method that combined face alignment with 3D face reconstruction, using the contour of the face in the 2D image by the regression algorithm. Lin et al [75] presented a reliable scheme for facial editing in video construction, further improved the generative adversarial network (GAN) so that the naturally edited face can be fused back into the video, and effectively reduced identity loss and semantic entanglement. Chu et al [76] developed a parametric face modeling framework, which gathered a large amount of data related to face parameters, then used the Kriging method to characterize the facial parameters and 3D facial synthesis.…”

Section: Human Body Modelingmentioning

confidence: 99%

“…In addition, preserving the identity details of real human faces plays an important role in accurately confirming the identity of the HDT model in the metaverse. Lin et al [75] implemented controllable face editing in video reconstruction, realized high-resolution and realistic face generation, and ensured the operability and high fidelity of HDT. This method achieved prominent identity preservation and semantic unwrapping in controllable face editing, which was superior to the most advanced method.…”

Section: Daily Life (General) Domainmentioning

confidence: 99%

See 1 more Smart Citation

Human Digital Twin: A Survey

Lin

Chen

Ali

et al. 2022

Preprint

View full text Add to dashboard Cite

Digital twin has recently attracted growing attention, leading to intensive research and applications. Along with this, a new research area, dubbed as "human digital twin" (HDT), has emerged. Similar to the conception of digital twin, HDT is referred to as the replica of a physical-world human in the digital world. Nevertheless, HDT is much more complicated and delicate compared to digital twins of any physical systems and processes, due to humans' dynamic and evolutionary nature, including physical, behavioral, social, physiological, psychological, cognitive, and biological dimensions. Studies on HDT are limited, and the research is still in its infancy. In this paper, we first examine the inception, development, and application of the digital twin concept, providing a context within which we formally define and characterize HDT based on the similarities and differences between digital twin and HDT. Then we conduct an extensive literature review on HDT research, analyzing underpinning technologies and establishing typical frameworks in which the core HDT functions or components are organized. Built upon the findings from the above work, we propose a generic architecture for the HDT system and describe the core function blocks and corresponding technologies. Following this, we present the state of the art of HDT technologies and applications in the healthcare, industry, and daily life domain. Finally, we discuss various issues related to the development of HDT and point out the trends and challenges of future HDT research and development.

show abstract

Section: Human Body Modelingmentioning

confidence: 99%

Section: Daily Life (General) Domainmentioning

confidence: 99%