Exportar Publicação

Zubair, M., Nunes, P., Conti, C. & Soares, L. D. (2025). LFVS-Mamba: State-Space Model for Light Field View Synthesis. 2025 International Conference on Visual Communications and Image Processing (VCIP).

M. Zubair et al.,  "LFVS-Mamba: State-Space Model for Light Field View Synthesis", in 2025 Int. Conf. on Visual Communications and Image Processing (VCIP), Klagenfurt, Austria, 2025

@misc{zubair2025_1773719026583,
	author = "Zubair, M. and Nunes, P. and Conti, C. and Soares, L. D.",
	title = "LFVS-Mamba: State-Space Model for Light Field View Synthesis",
	year = "2025",
	url = "https://ieeexplore.ieee.org/document/11396913"
}

TY  - CPAPER
TI  - LFVS-Mamba: State-Space Model for Light Field View Synthesis
T2  - 2025 International Conference on Visual Communications and Image Processing (VCIP)
AU  - Zubair, M.
AU  - Nunes, P.
AU  - Conti, C.
AU  - Soares, L. D.
PY  - 2025
CY  - Klagenfurt, Austria
UR  - https://ieeexplore.ieee.org/document/11396913
AB  - Light Field View Synthesis (LFVS) methods using Convolutional Neural Networks (CNNs) and Vision Transformers (VTs) have been extensively studied: CNNs excel at learning local spatial features via hierarchical receptive fields but cannot capture long-range global dependencies, while VTs inherently model global context through self-attention at the cost of quadratic computation and memory complexity. To address these issues, we propose LFVS-Mamba, which integrates a State-Space Module (SSM) with a Selective Scanning Mechanism to efficiently capture long-range dependencies. LFVS-Mamba processes 2D slices of the 4D LF to fully exploit spatial context, complementary angular information, and depth cues. The LFVS-Mamba comprises three modules to progressively synthesize dense LFs: (i) Shallow Feature Extraction (SFE), (ii) Spatial-Angular Depth Feature Extraction (SADFE), and (iii) Angular Upsampling (AU). Experimental results on standard LF benchmarks demonstrate that LFVS-Mamba consistently outperforms existing methods.
ER  -