The availability of massive public image datasets appears to have hardly been exploited in image compression. In this work, we present a novel framework for image compression based on human image generation and publicly available images as "side information." Our framework consists of one human who describes images using text instructions to another, who is tasked with reconstructing the original image to the first human's satisfaction. These image reconstructions were then rated by human scorers on the Amazon Mechanical Turk platform and compared to reconstructions obtained by existing image compressors. While this setup lacks certain components typical of traditional compressors, the insights gained from these experiments offer a new perspective on designing image compressors of the future.
The Santa Clara Valley chapters of the IEEE Information Theory and Signal Processing societies are co-sponsors this event.
Irena Fischer-Hwang is a PhD student in the electrical engineering department. Her advisor is Professor Tsachy Weissman. Her doctoral work is split between developing computational tools for analyzing genomic sequencing data, exploring novel image compression techniques, and analyzing public data sets in collaboration with data journalists to aid investigative journalism. She is a 2018 Brown Institute for Media Innovation Magic Grantee.