Exportar Publicação
A publicação pode ser exportada nos seguintes formatos: referência da APA (American Psychological Association), referência do IEEE (Institute of Electrical and Electronics Engineers), BibTeX e RIS.
Zubair, M., Nunes, P., Conti, C. & Soares, L. D. (2024). Light Field View Synthesis Using Deformable Convolutional Neural Networks. In 2024 Picture Coding Symposium (PCS). (pp. 1-5). Taichung, Taiwan: IEEE.
M. Zubair et al., "Light Field View Synthesis Using Deformable Convolutional Neural Networks", in 2024 Picture Coding Symp. (PCS), Taichung, Taiwan, IEEE, 2024, pp. 1-5
@inproceedings{zubair2024_1734953563103, author = "Zubair, M. and Nunes, P. and Conti, C. and Soares, L. D.", title = "Light Field View Synthesis Using Deformable Convolutional Neural Networks", booktitle = "2024 Picture Coding Symposium (PCS)", year = "2024", editor = "", volume = "", number = "", series = "", doi = "10.1109/PCS60826.2024.10566360", pages = "1-5", publisher = "IEEE", address = "Taichung, Taiwan", organization = "", url = "https://ieeexplore.ieee.org/document/10566360" }
TY - CPAPER TI - Light Field View Synthesis Using Deformable Convolutional Neural Networks T2 - 2024 Picture Coding Symposium (PCS) AU - Zubair, M. AU - Nunes, P. AU - Conti, C. AU - Soares, L. D. PY - 2024 SP - 1-5 DO - 10.1109/PCS60826.2024.10566360 CY - Taichung, Taiwan UR - https://ieeexplore.ieee.org/document/10566360 AB - 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. ER -