Mostra el registre d'ítem simple
Multi-view image fusion
dc.contributor.author | Comino Trinidad, Marc |
dc.contributor.author | Martin Brualla, Ricardo |
dc.contributor.author | Kainz, Florian |
dc.contributor.author | Kontkanen, Janne |
dc.contributor.other | Universitat Politècnica de Catalunya. Doctorat en Computació |
dc.date.accessioned | 2020-04-14T09:31:57Z |
dc.date.available | 2020-04-14T09:31:57Z |
dc.date.issued | 2019 |
dc.identifier.citation | Comino, M. [et al.]. Multi-view image fusion. A: IEEE International Conference on Computer Vision. "2019 International Conference on Computer Vision: 27 October–2 November 2019, Seoul, Korea: proceedings". 2019, p. 4100-4109. |
dc.identifier.other | http://openaccess.thecvf.com/content_ICCV_2019/html/Trinidad_Multi-View_Image_Fusion_ICCV_2019_paper.html |
dc.identifier.uri | http://hdl.handle.net/2117/183286 |
dc.description.abstract | We present an end-to-end learned system for fusing multiple misaligned photographs of the same scene into a chosen target view. We demonstrate three use cases: 1) color transfer for inferring color for a monochrome view, 2) HDR fusion for merging misaligned bracketed exposures, and 3) detail transfer for reprojecting a high definition image to the point of view of an affordable VR180-camera. While the system can be trained end-to-end, it consists of three distinct steps: feature extraction, image warping and fusion. We present a novel cascaded feature extraction method that enables us to synergetically learn optical flow at different resolution levels. We show that this significantly improves the network’s ability to learn large disparities. Finally, we demonstrate that our alignment architecture outperforms a state-of-the art optical flow network on the image warping task when both systems are trained in an identical manner. |
dc.format.extent | 10 p. |
dc.language.iso | eng |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Infografia |
dc.subject.lcsh | Color computer graphics |
dc.subject.lcsh | Machine learning |
dc.subject.other | Cameras |
dc.subject.other | Image color analysis |
dc.subject.other | Feature extraction |
dc.subject.other | Optical imaging |
dc.subject.other | Image resolution |
dc.subject.other | Computer architecture |
dc.subject.other | Image fusion |
dc.title | Multi-view image fusion |
dc.type | Conference report |
dc.subject.lemac | Infografia en color |
dc.subject.lemac | Aprenentatge automàtic |
dc.contributor.group | Universitat Politècnica de Catalunya. ViRVIG - Grup de Recerca en Visualització, Realitat Virtual i Interacció Gràfica |
dc.identifier.doi | 10.1109/ICCV.2019.00420 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | https://ieeexplore.ieee.org/document/9009997 |
dc.rights.access | Open Access |
local.identifier.drac | 27009656 |
dc.description.version | Postprint (author's final draft) |
dc.relation.projectid | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TIN2017-88515-C2-1-R/ES/VISUALIZACION, MODELADO, SIMULACION E INTERACCION CON MODELOS 3D. APLICACIONES EN CIENCIAS DE LA VIDA Y ENTORNOS RURALES Y URBANOS/ |
local.citation.author | Comino, M.; Martin, R.; Kainz, F.; Kontkanen, J. |
local.citation.contributor | IEEE International Conference on Computer Vision |
local.citation.publicationName | 2019 International Conference on Computer Vision: 27 October–2 November 2019, Seoul, Korea: proceedings |
local.citation.startingPage | 4100 |
local.citation.endingPage | 4109 |