论文标题
使用可变形卷积的光场图像超分辨率
Light Field Image Super-Resolution Using Deformable Convolution
论文作者
论文摘要
光场（LF）摄像机可以从多个角度录制场景，从而引入有益的角度信息以进行图像超分辨率（SR）。但是，由于LF图像之间的差异，将角度信息纳入角度是有挑战性的。在本文中，我们提出了一个可变形的卷积网络（即LF-DFNET）来处理LF Image SR的差异问题。具体而言，我们为特征级比对设计了一个可变形的比对模块（ADAM）。基于亚当，我们进一步提出了一种收集和分布方法，以在中心视图功能和每个侧视功能之间执行双向对齐。使用我们的方法，可以将角度信息充分合并并编码为每种视图的特征，从而使所有LF图像的SR重建有益于。此外，我们开发了一个基线可调的LF数据集，以评估不同差异变化下的SR性能。对公众和我们自我开发的数据集进行了实验证明了我们方法的优势。我们的LF-DFNET可以生成具有更忠实的细节的高分辨率图像，并实现最新的重建精度。此外，我们的LF-DFNET对差异的变化更为强大，这在文献中尚未得到很好的解决。
Light field (LF) cameras can record scenes from multiple perspectives, and thus introduce beneficial angular information for image super-resolution (SR). However, it is challenging to incorporate angular information due to disparities among LF images. In this paper, we propose a deformable convolution network (i.e., LF-DFnet) to handle the disparity problem for LF image SR. Specifically, we design an angular deformable alignment module (ADAM) for feature-level alignment. Based on ADAM, we further propose a collect-and-distribute approach to perform bidirectional alignment between the center-view feature and each side-view feature. Using our approach, angular information can be well incorporated and encoded into features of each view, which benefits the SR reconstruction of all LF images. Moreover, we develop a baseline-adjustable LF dataset to evaluate SR performance under different disparity variations. Experiments on both public and our self-developed datasets have demonstrated the superiority of our method. Our LF-DFnet can generate high-resolution images with more faithful details and achieve state-of-the-art reconstruction accuracy. Besides, our LF-DFnet is more robust to disparity variations, which has not been well addressed in literature.
