Densely-sampled light field (LF) image is drawing increased attention for its wide applications in 3D reconstruction, digital refocusing, depth estimation, and virtual/augmented reality, et al. In order to reconstruct a densely-sampled LF with high angular resolution, many computational methods have been proposed. However, most existing methods consider LF angular reconstruction based on neighboring views, local epipolar plane images (EPIs) or EPI volume information, which overlook the rich LF angular information and fail to restore more texture details, especially for occlusion regions. In order to mitigate this problem, we introduce a multi-angular epipolar geometry (MA-EG) structure for LF angular reconstruction. The MA-EG structure contains multi-angular directional LF geometry information and can provide multi-angular geometry characteristics in LF reconstruction process, which benefits in recovering more texture details. Based on the MA-EG structure, we further put forward a multi-angular LF angular reconstruction network (MALFRNet) to learn a mapping from sparse LF to a densely-sampled LF. The proposed MALFRNet adopts a multi-stream framework, which can fully explore rich LF angular information and implicitly learn LF angular consistency and spatial geometry information from LF MA-EG. Comprehensive experiments on real-world and synthetic LF scenes demonstrate that the proposed MALFRNet can recover more texture details and achieve a better reconstruction quality. Moreover, ablation studies and LF depth estimation applications also illustrate the advantages of using more angular information in LF angular reconstruction through the proposed MALFRNet.

中文翻译：

---

基于多角对极几何的光场角重建网络

密集采样光场 (LF) 图像因其在 3D 重建、数字重新聚焦、深度估计和虚拟/增强现实等方面的广泛应用而受到越来越多的关注。为了重建具有高角分辨率的密集采样LF，已经提出了许多计算方法。然而，现有的大多数方法都考虑了基于相邻视图、局部极平面图像（EPI）或 EPI 体积信息的 LF 角度重建，这忽略了丰富的 LF 角度信息并且无法恢复更多的纹理细节，尤其是对于遮挡区域。为了缓解这个问题，我们引入了一种用于 LF 角度重建的多角度对极几何 (MA-EG) 结构。MA-EG结构包含多角度定向LF几何信息，可以在LF重建过程中提供多角度几何特征，有利于恢复更多的纹理细节。基于MA-EG结构，我们进一步提出了一个多角度LF角度重建网络（MALFRNet）来学习从稀疏LF到密集采样LF的映射。所提出的 MALFRNet 采用多流框架，可以充分挖掘丰富的 LF 角度信息，并从 LF MA-EG 隐式学习 LF 角度一致性和空间几何信息。对真实世界和合成低频场景的综合实验表明，所提出的 MALFRNet 可以恢复更多的纹理细节并实现更好的重建质量。而且，