Figures
Fig 1 appears incorrectly in the published article. Please see the correct Fig 1 and its caption here. The publisher apologizes for the error.
The input is split into two components: i) the downsampled warped image and ii) the metadata, which contains a compressed version of the warp kernel. These two components are jointly used for recovering the original input. Since the warp kernel is image-dependent, we must send it as part of the compressed file, which creates extra overhead relative to an image-independent compression technique, such as uniform sampling. However, if the metadata can be compressed extremely compactly, the overall compression ratio can still be significant.
Reference
Citation: The PLOS ONE Staff (2016) Correction: Context-Aware Image Compression. PLoS ONE 11(12): e0168630. https://doi.org/10.1371/journal.pone.0168630
Published: December 12, 2016
Copyright: © 2016 The PLOS ONE Staff. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.