Publicación:
RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects

dc.contributor.authorKirch, Sascha
dc.contributor.authorOlyunina, Valeria
dc.contributor.authorOndřej, Jan
dc.contributor.authorPagés, Rafael
dc.contributor.authorMartín Gutiérrez, Sergio
dc.contributor.authorPérez Molina, Clara María
dc.contributor.orcidhttps://orcid.org/0000-0002-5578-7555
dc.contributor.orcidhttps://orcid.org/0009-0000-9766-5057
dc.contributor.orcidhttps://orcid.org/0000-0002-5409-1521
dc.contributor.orcidhttps://orcid.org/0000-0002-5691-9580
dc.date.accessioned2024-10-14T07:03:44Z
dc.date.available2024-10-14T07:03:44Z
dc.date.issued2023-09-04
dc.descriptionEste es el manuscrito aceptado del artículo. La versión registrada fue publicada por primera vez en EEE Access, vol. 11, pp. 99111-99129, 2023, , está disponible en línea en el sitio web del editor: https://doi.org/10.1109/ACCESS.2023.3312017 This is the accepted manuscript of the article. The registered version was first published in EEE Access, vol. 11, pp. 99111-99129, 2023, is available online at the publisher's website: https://doi.org/10.1109/ACCESS.2023.3312017
dc.description.abstractWe present RGB-D-Fusion, a multi-modal conditional denoising diffusion probabilistic model to generate high resolution depth maps from low-resolution monocular RGB images of humanoid subjects. Accurately representing the human body in 3D is a very active research field given its wide variety of applications. Most 3D reconstruction algorithms rely on depth maps, either coming from low-resolution consumer-level depth sensors, or from monocular depth estimation from standard images. While many modern frameworks use VAEs or GANs for monocular depth estimation, we leverage recent advances in the field of diffusion denoising probabilistic models. We implement a multi-stage conditional diffusion model that first generates a low-resolution depth map conditioned on an image and then upsamples the depth map conditioned on a low-resolution RGB-D image. We further introduce a novel augmentation technique, depth noise augmentation, to increase the robustness of our super-resolution model. Lastly, we show how our method performs on a wide variety of humans with different body types, clothing and poses.en
dc.description.versionversión final
dc.identifier.citationS. Kirch, V. Olyunina, J. Ondřej, R. Pagés, S. Martín and C. Pérez-Molina, "RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects," in IEEE Access, vol. 11, pp. 99111-99129, 2023, doi: https://doi.org/10.1109/ACCESS.2023.3312017
dc.identifier.doihttps://doi.org/10.1109/ACCESS.2023.3312017
dc.identifier.issn2169-3536; e-ISSN: 2169-3536
dc.identifier.urihttps://hdl.handle.net/20.500.14468/24033
dc.journal.titleIEEE Access
dc.journal.volume11
dc.language.isoen
dc.page.final99129
dc.page.initial99111
dc.publisherIEEE Xplore
dc.relation.centerFacultades y escuelas::E.T.S. de Ingenieros Industriales
dc.relation.departmentIngeniería Eléctrica, Electrónica, Control, Telemática y Química Aplicada a la Ingeniería
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
dc.subject33 Ciencias Tecnológicas
dc.subject.keywordssolid modelingen
dc.subject.keywordsdata modelsen
dc.subject.keywordsestimationen
dc.subject.keywordsthree-dimensional displaysen
dc.subject.keywordsnoise reductionen
dc.subject.keywordscamerasen
dc.subject.keywordsprobabilistic logicen
dc.subject.keywordsdiffusion processesen
dc.subject.keywordsdeep learningen
dc.subject.keywordssuperresolutionen
dc.subject.keywordsaugmented realityen
dc.subject.keywordsvirtual realityen
dc.subject.keywordsdiffusion modelsen
dc.subject.keywordsgenerative deep learningen
dc.subject.keywordsmonocular depth estimationen
dc.subject.keywordsdepth super-resolutionen
dc.subject.keywordsmulti-modalen
dc.subject.keywordsaugmented-realityen
dc.subject.keywordsvirtual-realityen
dc.titleRGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjectsen
dc.typeartículoes
dc.typejournal articleen
dspace.entity.typePublication
relation.isAuthorOfPublication634efe13-d6e9-4ddb-b4e6-565d60469512
relation.isAuthorOfPublication5b060333-a864-4fd5-b494-4726487f4ba6
relation.isAuthorOfPublication.latestForDiscovery634efe13-d6e9-4ddb-b4e6-565d60469512
Archivos
Bloque original
Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
MartinGutierrezSergio_RGB-D Fusion.pdf
Tamaño:
20.57 MB
Formato:
Adobe Portable Document Format
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
3.62 KB
Formato:
Item-specific license agreed to upon submission
Descripción: