… In this section, we discuss our proposed multi-stream view reconstruction network for LF
image compression. The entire flow graph of the proposed LF image compression framework is …

… compression performance. In this paper, we construct a geometry-aware view reconstruction
network for LF image compression… information are fully fused for high-quality reconstruction. …

… In this paper, we present a LF image compression framework driven by a generative
adversarial network (GAN)-based sub-aperture image (SAI) generation and a cascaded …

… We apply dilated convolution with different dilation factors to increase the receptive fields,
which capture multi-scale features in the image. Finally, we fuse multiple feature information to …

… receptive field. After the extraction of the feature, the deep reconstruction network cascades
… -linear mapping and increase receptive fields. Finally, the feature aggregation produces the …

… field operations can cause image structure change, for example compression and reconstruction,
… Image structure is widely used in many image quality assessment (IQA) metrics due to …

… After getting the high dimensional image feature, the deep reconstruction network … the
network non-linear and its receptive field. This non-linear mapping operation is expressed as …

… It is important to note that there is no consensus in the field for which metric best represents
… -established metric for comparing lossy image compression algorithms, and the more recent …

… technology has been developed and applied in many fields. … and the reconstruction network,
the reconstruction network can … obtain the information needed for reconstruction adaptively. …

… resolution) at 15 fps over the network. Liu et al. [48] also developed an 8 × 8 dynamic light
field streaming system over broadband network. Typical camera array systems are bulky and …