Utilize este identificador para referenciar este registo: http://hdl.handle.net/10071/34291
Autoria: Zubair, M.
Nunes, P.
Conti, C.
Soares, L. D.
Data: 2024
Título próprio: Light field view synthesis using deformable convolutional neural networks
Título e volume do livro: 2024 Picture Coding Symposium, PCS 2024, Proceedings
Paginação: 1 - 5
Título do evento: 2024 Picture Coding Symposium, PCS 2024
Referência bibliográfica: Zubair, M., Nunes, P., Conti, C., & Soares, L. D. (2024). Light field view synthesis using deformable convolutional neural networks. 2024 Picture Coding Symposium, PCS 2024, Proceedings. IEEE. https://doi.org/10.1109/PCS60826.2024.10566360
ISBN: 979-835035848-3
DOI (Digital Object Identifier): 10.1109/PCS60826.2024.10566360
Palavras-chave: Light field view synthesis
Deformable convolution
Depth-wise separable convolution
Geometry-aware network
Resumo: 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 methods have been proposed. This paper follows a similar approach to Liu et al. [1] but using deformable convolutions to improve the view synthesis performance and depth-wise separable convolutions to reduce the amount of model parameters. The proposed framework consists of two main modules: i) a multi-representation view synthesis module to extract features from different LF representations of the sparse LF, and ii) a geometry-aware refinement module to synthesize a dense LF by exploring the structural characteristics of the corresponding sparse LF. Experimental results over various benchmarks demonstrate the superiority of the proposed method when compared to state-of-the-art ones. The code is available at https://github.com/MSP-IUL/deformable lfvs.
Arbitragem científica: yes
Acesso: Acesso Aberto
Aparece nas coleções:IT-CRI - Comunicações a conferências internacionais

Ficheiros deste registo:
Ficheiro TamanhoFormato 
conferenceObject_104512.pdf
  Restricted Access
1,6 MBAdobe PDFVer/Abrir Request a copy


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpaceOrkut
Formato BibTex mendeley Endnote Logotipo do DeGóis Logotipo do Orcid 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.