A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2006.09965v3.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
High-Fidelity Generative Image Compression
[article]
<span title="2020-10-23">2020</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2020-06-17">2020</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.09965v1">arXiv:2006.09965v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xhj7y5ylczabzgiz7hrigof2pu">fatcat:xhj7y5ylczabzgiz7hrigof2pu</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.09965v1">arXiv:2006.09965v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xhj7y5ylczabzgiz7hrigof2pu">fatcat:xhj7y5ylczabzgiz7hrigof2pu</a> </span>
<span title="2020-07-10">2020</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.09965v2">arXiv:2006.09965v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wq7qhbxdnrcsridulr5r3flzre">fatcat:wq7qhbxdnrcsridulr5r3flzre</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.09965v2">arXiv:2006.09965v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wq7qhbxdnrcsridulr5r3flzre">fatcat:wq7qhbxdnrcsridulr5r3flzre</a> </span>
We extensively study how to combine Generative Adversarial Networks and learned compression to obtain a state-of-the-art generative lossy compression system. In particular, we investigate normalization layers, generator and discriminator architectures, training strategies, as well as perceptual losses. In contrast to previous work, i) we obtain visually pleasing reconstructions that are perceptually similar to the input, ii) we operate in a broad range of bitrates, and iii) our approach can be
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.09965v3">arXiv:2006.09965v3</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/i7d6cpbeobfidf4jwqo2rt5fcm">fatcat:i7d6cpbeobfidf4jwqo2rt5fcm</a>
</span>
more »
... pplied to high-resolution images. We bridge the gap between rate-distortion-perception theory and practice by evaluating our approach both quantitatively with various perceptual metrics, and with a user study. The study shows that our method is preferred to previous approaches even if they use more than 2x the bitrate.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201029021612/https://arxiv.org/pdf/2006.09965v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/8f/22/8f22824d839cc6d4bb3b04af471c91198e7bfb39.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.09965v3" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>