Real-Time Depth Video-Based Rendering for 6-DoF HMD Navigation and Light Field Displays

This paper presents a novel approach to provide immersive free navigation with 6 Degrees of Freedom in real-time for natural and virtual scenery, for both static and dynamic content. Stemming from the state-of-the-art in Depth Image-Based Rendering and the OpenGL pipeline, this new View Synthesis me...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Daniele Bonatto, Sarah Fachada, Segolene Rogge, Adrian Munteanu, Gauthier Lafruit
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/f52a691319474da299d758aff8137569
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:f52a691319474da299d758aff8137569
record_format dspace
spelling oai:doaj.org-article:f52a691319474da299d758aff81375692021-11-09T00:03:36ZReal-Time Depth Video-Based Rendering for 6-DoF HMD Navigation and Light Field Displays2169-353610.1109/ACCESS.2021.3123529https://doaj.org/article/f52a691319474da299d758aff81375692021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9590541/https://doaj.org/toc/2169-3536This paper presents a novel approach to provide immersive free navigation with 6 Degrees of Freedom in real-time for natural and virtual scenery, for both static and dynamic content. Stemming from the state-of-the-art in Depth Image-Based Rendering and the OpenGL pipeline, this new View Synthesis method achieves free navigation at up to 90 FPS and can take any number of input views with their corresponding depth maps as priors. Video content can be played thanks to GPU decompression, supporting free navigation with full parallax in real-time. To render a novel viewpoint, each selected input view is warped using the camera pose and associated depth map, using an implicit 3D representation. The warped views are then blended all together to generate the chosen virtual view. Various view blending approaches specifically designed to avoid visual artifacts are compared. Using as few as four input views appears to be an optimal trade-off between computation time and quality, allowing to synthesize high-quality stereoscopic views in real-time, offering a genuine immersive virtual reality experience. Additionally, the proposed approach provides high-quality rendering of a 3D scenery on holographic light field displays. Our results are comparable - objectively and subjectively - to the state of the art view synthesis tools NeRF and LLFF, while maintaining an overall lower complexity and real-time rendering.Daniele BonattoSarah FachadaSegolene RoggeAdrian MunteanuGauthier LafruitIEEEarticleVirtual realitystereo image processingstereo visionfree viewpoint navigationreference view synthesizerreal-time view synthesisElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 146868-146887 (2021)
institution DOAJ
collection DOAJ
language EN
topic Virtual reality
stereo image processing
stereo vision
free viewpoint navigation
reference view synthesizer
real-time view synthesis
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
spellingShingle Virtual reality
stereo image processing
stereo vision
free viewpoint navigation
reference view synthesizer
real-time view synthesis
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
Daniele Bonatto
Sarah Fachada
Segolene Rogge
Adrian Munteanu
Gauthier Lafruit
Real-Time Depth Video-Based Rendering for 6-DoF HMD Navigation and Light Field Displays
description This paper presents a novel approach to provide immersive free navigation with 6 Degrees of Freedom in real-time for natural and virtual scenery, for both static and dynamic content. Stemming from the state-of-the-art in Depth Image-Based Rendering and the OpenGL pipeline, this new View Synthesis method achieves free navigation at up to 90 FPS and can take any number of input views with their corresponding depth maps as priors. Video content can be played thanks to GPU decompression, supporting free navigation with full parallax in real-time. To render a novel viewpoint, each selected input view is warped using the camera pose and associated depth map, using an implicit 3D representation. The warped views are then blended all together to generate the chosen virtual view. Various view blending approaches specifically designed to avoid visual artifacts are compared. Using as few as four input views appears to be an optimal trade-off between computation time and quality, allowing to synthesize high-quality stereoscopic views in real-time, offering a genuine immersive virtual reality experience. Additionally, the proposed approach provides high-quality rendering of a 3D scenery on holographic light field displays. Our results are comparable - objectively and subjectively - to the state of the art view synthesis tools NeRF and LLFF, while maintaining an overall lower complexity and real-time rendering.
format article
author Daniele Bonatto
Sarah Fachada
Segolene Rogge
Adrian Munteanu
Gauthier Lafruit
author_facet Daniele Bonatto
Sarah Fachada
Segolene Rogge
Adrian Munteanu
Gauthier Lafruit
author_sort Daniele Bonatto
title Real-Time Depth Video-Based Rendering for 6-DoF HMD Navigation and Light Field Displays
title_short Real-Time Depth Video-Based Rendering for 6-DoF HMD Navigation and Light Field Displays
title_full Real-Time Depth Video-Based Rendering for 6-DoF HMD Navigation and Light Field Displays
title_fullStr Real-Time Depth Video-Based Rendering for 6-DoF HMD Navigation and Light Field Displays
title_full_unstemmed Real-Time Depth Video-Based Rendering for 6-DoF HMD Navigation and Light Field Displays
title_sort real-time depth video-based rendering for 6-dof hmd navigation and light field displays
publisher IEEE
publishDate 2021
url https://doaj.org/article/f52a691319474da299d758aff8137569
work_keys_str_mv AT danielebonatto realtimedepthvideobasedrenderingfor6dofhmdnavigationandlightfielddisplays
AT sarahfachada realtimedepthvideobasedrenderingfor6dofhmdnavigationandlightfielddisplays
AT segolenerogge realtimedepthvideobasedrenderingfor6dofhmdnavigationandlightfielddisplays
AT adrianmunteanu realtimedepthvideobasedrenderingfor6dofhmdnavigationandlightfielddisplays
AT gauthierlafruit realtimedepthvideobasedrenderingfor6dofhmdnavigationandlightfielddisplays
_version_ 1718441440955072512