RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación
Contribución de congreso (ConferenceOutput)
Virtual Experience Toolkit: Enhancing 3D Scene Virtualization from Real Environments through Computer Vision and Deep Learning Techniques
[EN] Over the past few decades, Virtual Reality (VR)
has emerged as a popular topic in a wide range of fields, such
as information technology and psychology, among others. One
reason for its importance was due to the ability to virtualize
real-world scenes. This process typically involves capturing data
from those scenes to generate accurate, detailed, and immersive
3D models. However, the creation of virtual content from realworld
scenes has traditionally relied on manual techniques, as
well as photogrammetry or Computer Vision (CV) algorithms.
This frequently yields time-intensive, less accurate, intricate,
and semi-automatic results. To tackle these limitations, a novel
framework called Virtual Experience Toolkit (VET) has been
proposed. It employs CV and Deep Learning (DL) techniques to
swiftly and seamlessly virtualize any 3D scenario from real indoor
environments. To demonstrate the effectiveness of VET, a diverse
dataset of virtualized 3D scenes was generated, supplementing the
information from the ScanNet dataset. VET has the potential to
significantly enhance the virtualization of 3D indoor scenarios
from real scenes, making the process easier, more precise, unified,
consistent, automated, and effective for a broad spectrum of VR
applications., The research leading to these results has received partial
funding from the European Commission under grant agreement N. 101017727 for the project EXPERIENCE.