论文标题
Sadn：通过空间 - 角度去相关的学习光场图像压缩
SADN: Learned Light Field Image Compression with Spatial-Angular Decorrelation
论文作者
论文摘要
光场图像成为沉浸式视频应用程序最有前途的媒体类型之一。在本文中，我们提出了一种新型的端到端空间角 - 角度相关网络（SADN），以实现高效光场图像压缩。与在光场图像中利用空间或角度一致性的现有方法不同，SADN通过扩张卷积和空间卷积在空间角相互作用中解散了角度和空间信息，并执行特征融合以压缩空间和角度信息。为了训练稳定且健壮的算法，提出并建造了由7549个光场图像组成的大规模数据集。该方法分别相对于H.266/VVC和H.265/HEVC间编码提供了2.137次和2.849倍的压缩效率。它还胜过端到端图像压缩网络的平均比比特率节省了79.6％，主观质量和光场一致性更高。
Light field image becomes one of the most promising media types for immersive video applications. In this paper, we propose a novel end-to-end spatial-angular-decorrelated network (SADN) for high-efficiency light field image compression. Different from the existing methods that exploit either spatial or angular consistency in the light field image, SADN decouples the angular and spatial information by dilation convolution and stride convolution in spatial-angular interaction, and performs feature fusion to compress spatial and angular information jointly. To train a stable and robust algorithm, a large-scale dataset consisting of 7549 light field images is proposed and built. The proposed method provides 2.137 times and 2.849 times higher compression efficiency relative to H.266/VVC and H.265/HEVC inter coding, respectively. It also outperforms the end-to-end image compression networks by an average of 79.6% bitrate saving with much higher subjective quality and light field consistency.
