Slope-Guided Mamba and Angular-Refined Transformer for Light Field Super-Resolution
For researchers in light field imaging, this work provides a hybrid architecture that improves geometric consistency and super-resolution quality, though it is an incremental improvement over existing methods.
The paper tackles light field super-resolution by addressing decoupled spatial-angular modeling and scan-geometry mismatch in existing methods. Their proposed SMART network achieves state-of-the-art performance, outperforming previous methods by 0.42 dB PSNR on five benchmarks.
Light Field Super-Resolution (LFSR) necessitates accurate modeling of spatial-angular correlations while preserving intrinsic 4D ray coherence. However, maintaining such high-dimensional consistency remains challenging, primarily due to two inherent limitations in prevailing modeling paradigms. First, spatial and angular dimensions are often modeled in a decoupled manner, restricting early cross-dimensional interaction and leading to geometric inconsistencies. Moreover, although continuous sequence modeling paradigms show promise in representing epipolar structures, their rigid scanning mechanisms fundamentally conflict with epipolar geometry, limiting geometry-aware feature aggregation. To address these challenges, we propose a hybrid light field super-resolution network, termed SMART, which integrates a Slope-Guided Mamba and an Angular-Refined Transformer to effectively overcome these limitations. Specifically, we introduce an angular-modulated spatial module to bridge the decoupling gap, incorporating angular priors to strengthen spatial-angular correlation modeling. To mitigate the scan-geometry mismatch, we propose a manifold-aligned trajectory module that enables geometry-consistent sequence modeling along epipolar structures. Experiments on five benchmarks demonstrate that SMART achieves state-of-the-art performance, surpassing previous methods by 0.42 dB (PSNR) with significantly reduced artifacts.