Elkady Ebrahem, Salem Ahmed, Kang Hyun-Soo, Suh Jae-Won
School of Electronics Engineering, College of Electrical and Computer Engineering, Chungbuk National University, 28644, Cheongju, South Korea.
Information Technology Department, Faculty of Computers and Information, Assiut University, 71526, Assiut, Egypt.
Sci Rep. 2024 Nov 30;14(1):29810. doi: 10.1038/s41598-024-81296-z.
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.
最近，由于密集多视图图像重建在三维重建、去遮挡、深度感知、显著性检测和突出物体识别等应用中的增强作用，其相关研究受到了广泛关注。本文介绍了一种重建高密度光场图像的方法，解决了在传感器分辨率限制下平衡角度和空间分辨率的挑战。我们提出了一种用于光场重建的三阶段网络架构，该架构能有效地处理密集的对极、空间和角度信息。我们的网络在第一阶段处理对极信息，第二阶段处理空间信息，第三阶段处理角度信息。通过从多个方向提取四边形对极特征，我们的模型构建了一个强大的特征层次结构以进行精确重建。我们在初始阶段采用权重共享来提高特征质量，同时保持模型的紧凑性。在真实世界和合成数据集上的实验结果表明，我们的方法在推理时间和重建质量上均优于现有方法。
