Abstract
Recent research on dense multi-view image reconstruction has attracted considerable attention, due to its enhancement of applications such as 3D reconstruction, de-occlusion, depth sensing, saliency detection, and prominent object identification. This paper introduces a method for reconstructing high-density light field images, addressing the challenge of balancing angular and spatial resolution within the constraints of sensor resolution. We propose a three-stage network architecture for LF reconstruction that processes dense epipolar, spatial, and angular information efficiently. Our network processes epipolar information in the first stage, spatial information in the second stage, and angular information in the third stage. By extracting quadrilateral epipolar features from multiple directions, our model constructs a robust feature hierarchy for accurate reconstruction. We employ weight sharing in the initial stage to enhance feature quality while maintaining a compact model. Experimental results on real-world and synthetic datasets demonstrate that our approach surpasses state-of-the-art methods in both inference time and reconstruction quality.