51 documents found, page 1 of 6
Unsupervised angularly consistent 4D light field segmentation using hyperpixels...
Hamad, M.; Conti, C.; Nunes, P.; Soares, L. D.Image segmentation is an essential initial stage in several computer vision applications. However, unsupervised image segmentation is still a challenging task in some cases such as when objects with a similar visual appearance overlap. Unlike 2D images, 4D Light Fields (LFs) convey both spatial and angular scene information facilitating depth/disparity estimation, which can be further used to guide the segmenta...
Light field view synthesis using deformable convolutional neural networks
Zubair, M.; Nunes, P.; Conti, C.; Soares, L. D.Light Field (LF) imaging has emerged as a technology that can simultaneously capture both intensity values and directions of light rays from real-world scenes. Densely sampled LFs are drawing increased attention for their wide application in 3D reconstruction, depth estimation, and digital refocusing. In order to synthesize additional views to obtain a LF with higher angular resolution, many learning-based meth...
Photoluminescent alginate-based composite inks for anti-counterfeiting security...
Cruz, B. D. D.; Correia, Daniela M.; Polícia, R.; Pereira, N.; Nunes, P.; Fernandes, M.; Tubio, C. R.; Botelho, G.; Lanceros-Méndez, S.Natural polymers have been increasingly explored for a wide range of applications as smart materials due to their unique properties, abundance, and sustainability attributes. In the present work, novel luminescent composite films based on sodium alginate (SA) and different amounts of the compounds sodium tetra(2- thenoyltrifluoroacetonate)europate (III) (Na[Eu(tta)4]) (5, 10 and 20% wt.) and 1-butyl-3-methylimi...
Hyperpixels: Flexible 4D over-segmentation for dense and sparse light fields
Hamad, M.; Conti, C.; Nunes, P.; Soares, L. D.4D Light Field (LF) imaging, since it conveys both spatial and angular scene information, can facilitate computer vision tasks and generate immersive experiences for end-users. A key challenge in 4D LF imaging is to flexibly and adaptively represent the included spatio-angular information to facilitate subsequent computer vision applications. Recently, image over-segmentation into homogenous regions with percep...
Efficient propagation method for angularly consistent 4D light field disparity ...
Hamad, M.; Conti, C.; Nunes, P.; Soares, L. D.Light Field (LF) imaging, since it conveys both spatial and angular scene information, can facilitate computer vision tasks such as depth/disparity estimation. Although disparity maps can be estimated for all LF views, most existing methods merely estimate depth/disparity for the central view and do not adequately deal with other LF views. However, having depth/disparity maps for all LF views can be useful for ...
View-consistent 4D Light Field style transfer using neural networks and over-se...
Hamad, M.; Conti, C.; Nunes, P.; Soares, L. D.Deep learning has shown promising results in several computer vision applications, such as style transfer applications. Style transfer aims at generating a new image by combining the content of one image with the style and color palette of another image. When applying style transfer to a 4D Light Field (LF) that represents the same scene from different angular perspectives, new challenges and requirements are i...
O cumprimento dos programas eleitorais em Portugal: Tendências, reformas políti...
Belchior, A. M.; Moury, C.; Hanenberg, L.; Nunes, P.Em que medida os partidos portugueses cumprem as promessas eleitorais? E este cumprimento corresponde a reformas de curto ou de longo prazo? Ainda: em que medida os veto players condicionam o cumprimento do mandato pelos governos? Este artigo centra-se nestas questões, analisando sete legislaturas, entre 1995 e 2019, e um total de 6367 promessas. Os resultados revelam que o nível de cumprimento é consistentemen...
ALFO: Adaptive light field over-segmentation
Hamad, M.; Conti, C.; Nunes, P.; Soares, L. D.Automatic image over-segmentation into superpixels has attracted increasing attention from researchers to apply it as a pre-processing step for several computer vision applications. In 4D Light Field (LF) imaging, image over-segmentation aims at achieving not only superpixel compactness and accuracy but also cross-view consistency. Due to the high dimensionality of 4D LF images, depth information can be estimat...
SLFS: Semi-supervised light-field foreground-background segmentation
Hamad, M.; Conti, C.; Almeida, A. M. de.; Nunes, P.; Soares, L. D.Efficient segmentation is a fundamental problem in computer vision and image processing. Achieving accurate segmentation for 4D light field images is a challenging task due to the huge amount of data involved and the intrinsic redundancy in this type of images. While automatic image segmentation is usually challenging, and because regions of interest are different for different users or tasks, this paper propos...
Sistema elétrico futuro baseado em renováveis e a sua dependência da variabilid...
Figueiredo, R.; Nunes, P.; Brito, M.C.RESUMO: A transição para sistemas elétricos baseados em renováveis tem sido crítica para o combate às alterações climáticas. Tal contribui para uma maior vulnerabilidade dos sistemas a variações do clima e do consumo elétrico no futuro. Com base nisto, este trabalho analisa o impacto que climas futuros e cenários de consumo terão num sistema elétrico com elevada penetração de renováveis. O caso de estudo é Port...