Tri-visualization feature extraction for light field angular super-resolution

Light field angular super-resolution (LFASR) aims to reconstruct densely sampled angular views from sparsely captured inputs, enabling high-fidelity rendering, refocusing, and depth estimation. In this paper, we propose a novel LFASR framework that employs a tri-visualization feature extraction strategy, which jointly processes Sub-Aperture Images (SAIs), Epipolar Plane Images (EPIs), and Macro-Pixel Images (MacroPIs) to comprehensively exploit the spatial-angular structure of light fields. These complementary representations are processed in parallel to extract diverse and informative features, which are then refined through a deep spatial aggregation module composed of residual blocks. The proposed pipeline consists of three key stages: Early Feature Extraction (EFE), Advanced Feature Refinement (AFR), and Angular Super-Resolution (ASR). Extensive experiments on both synthetic and real-world datasets demonstrate that our method achieves strong performance in terms of PSNR and SSIM, while maintaining strong generalization and robustness in challenging scenarios, including occlusions and large disparity variations. Moreover, qualitative evaluations confirm the method's ability to preserve epipolar consistency and structural integrity across synthesized views, making it a reliable and efficient solution for practical LFASR applications.