Shearlet Transform (ST) has been instrumental for the Densely-Sampled Light Field (DSLF) reconstruction, as it sparsifies the underlying Epipolar-Plane Images (EPIs). The sought sparsification is implemented through an iterative regularization, which tends to be slow because of the time spent on domain transformations for dozens of iterations. To overcome this limitation, this letter proposes a novel self-supervised DSLF reconstruction method, CycleST, which employs ST and cycle consistency. Specifically, CycleST is composed of an encoder-decoder network and a residual learning strategy that restore the shearlet coefficients of densely-sampled EPIs using EPI-reconstruction and cycle-consistency losses. CycleST is a self-supervised approach that can be trained solely on Sparsely-Sampled Light Fields (SSLFs) with small disparity ranges ($\leqslant$ 8 pixels). Experimental results of DSLF reconstruction on SSLFs with large disparity ranges (16 - 32 pixels) demonstrate the effectiveness and efficiency of the proposed CycleST method. Furthermore, CycleST achieves $\sim$ 9x speedup over ST, at least.

中文翻译：

---

使用Shearlet变换和循环一致性的自监督光场重建

Shearlet 变换 (ST) 有助于密集采样光场 (DSLF) 重建，因为它可以稀疏化底层的对极平面图像 (EPI)。寻求的稀疏化是通过迭代正则化实现的，由于在域转换上花费了数十次迭代的时间，因此往往很慢。为了克服这个限制，这封信提出了一种新的自监督 DSLF 重建方法 CycleST，它采用了 ST 和循环一致性。具体来说，CycleST 由编码器-解码器网络和残差学习策略组成，该策略使用 EPI 重建和循环一致性损失来恢复密集采样的 EPI 的剪切系数。CycleST 是一种自我监督的方法，可以仅在具有小视差范围的稀疏采样光场 (SSLF) 上进行训练（$\leqslant$8 像素）。在具有大视差范围（16 - 32 像素）的 SSLF 上进行 DSLF 重建的实验结果证明了所提出的 CycleST 方法的有效性和效率。此外，CycleST 实现了$\sim$ 至少比 ST 快 9 倍。