Publicación: RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects
dc.contributor.author | Kirch, Sascha | |
dc.contributor.author | Olyunina, Valeria | |
dc.contributor.author | Ondřej, Jan | |
dc.contributor.author | Pagés, Rafael | |
dc.contributor.author | Martín Gutiérrez, Sergio | |
dc.contributor.author | Pérez Molina, Clara María | |
dc.contributor.orcid | https://orcid.org/0000-0002-5578-7555 | |
dc.contributor.orcid | https://orcid.org/0009-0000-9766-5057 | |
dc.contributor.orcid | https://orcid.org/0000-0002-5409-1521 | |
dc.contributor.orcid | https://orcid.org/0000-0002-5691-9580 | |
dc.date.accessioned | 2024-10-14T07:03:44Z | |
dc.date.available | 2024-10-14T07:03:44Z | |
dc.date.issued | 2023-09-04 | |
dc.description | Este 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.abstract | We 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.version | versión final | |
dc.identifier.citation | S. 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.doi | https://doi.org/10.1109/ACCESS.2023.3312017 | |
dc.identifier.issn | 2169-3536; e-ISSN: 2169-3536 | |
dc.identifier.uri | https://hdl.handle.net/20.500.14468/24033 | |
dc.journal.title | IEEE Access | |
dc.journal.volume | 11 | |
dc.language.iso | en | |
dc.page.final | 99129 | |
dc.page.initial | 99111 | |
dc.publisher | IEEE Xplore | |
dc.relation.center | Facultades y escuelas::E.T.S. de Ingenieros Industriales | |
dc.relation.department | Ingeniería Eléctrica, Electrónica, Control, Telemática y Química Aplicada a la Ingeniería | |
dc.rights | info:eu-repo/semantics/openAccess | |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/deed.es | |
dc.subject | 33 Ciencias Tecnológicas | |
dc.subject.keywords | solid modeling | en |
dc.subject.keywords | data models | en |
dc.subject.keywords | estimation | en |
dc.subject.keywords | three-dimensional displays | en |
dc.subject.keywords | noise reduction | en |
dc.subject.keywords | cameras | en |
dc.subject.keywords | probabilistic logic | en |
dc.subject.keywords | diffusion processes | en |
dc.subject.keywords | deep learning | en |
dc.subject.keywords | superresolution | en |
dc.subject.keywords | augmented reality | en |
dc.subject.keywords | virtual reality | en |
dc.subject.keywords | diffusion models | en |
dc.subject.keywords | generative deep learning | en |
dc.subject.keywords | monocular depth estimation | en |
dc.subject.keywords | depth super-resolution | en |
dc.subject.keywords | multi-modal | en |
dc.subject.keywords | augmented-reality | en |
dc.subject.keywords | virtual-reality | en |
dc.title | RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects | en |
dc.type | artículo | es |
dc.type | journal article | en |
dspace.entity.type | Publication | |
relation.isAuthorOfPublication | 634efe13-d6e9-4ddb-b4e6-565d60469512 | |
relation.isAuthorOfPublication | 5b060333-a864-4fd5-b494-4726487f4ba6 | |
relation.isAuthorOfPublication.latestForDiscovery | 634efe13-d6e9-4ddb-b4e6-565d60469512 |
Archivos
Bloque original
1 - 1 de 1
Cargando...
- Nombre:
- MartinGutierrezSergio_RGB-D Fusion.pdf
- Tamaño:
- 20.57 MB
- Formato:
- Adobe Portable Document Format
Bloque de licencias
1 - 1 de 1
No hay miniatura disponible
- Nombre:
- license.txt
- Tamaño:
- 3.62 KB
- Formato:
- Item-specific license agreed to upon submission
- Descripción: