Artificial Intelligence | News | Insights | AiThority
[bsfp-cryptocurrency style=”widget-18″ align=”marquee” columns=”6″ coins=”selected” coins-count=”6″ coins-selected=”BTC,ETH,XRP,LTC,EOS,ADA,XLM,NEO,LTC,EOS,XEM,DASH,USDT,BNB,QTUM,XVG,ONT,ZEC,STEEM” currency=”USD” title=”Cryptocurrency Widget” show_title=”0″ icon=”” scheme=”light” bs-show-desktop=”1″ bs-show-tablet=”1″ bs-show-phone=”1″ custom-css-class=”” custom-id=”” css=”.vc_custom_1523079266073{margin-bottom: 0px !important;padding-top: 0px !important;padding-bottom: 0px !important;}”]

InterDigital’s CompareAI App Allows Comparative Testing of AI-based Image Compression Algorithms on Consumer Devices

CompareAI is the first iOS app to enable experimentation with a library of state-of-the-art Deep Learning-based image compression algorithms on real world, resource-limited devices

InterDigital, Inc., a mobile and video technology research and development company, announced it has translated its deep learning-based image compression research into the first AI-based image compression app—CompareAI. Running offline and on resource-constrained consumer hardware, CompareAI allows researchers and developers to experiment with and compare a wide range of compute-intensive image compression techniques in “real world” scenarios.

CompareAI features 15 deep learning-based compression models and includes a deep learning-based image encoder, a decoder, and an entropy coder to generate bitstreams comparable to traditional image compression algorithms, which had previously required dedicated Graphics Processing Units (GPUs).

Recommended AI News: Seismic Chooses Vengreso for Virtual Sales Training Partnership

Related Posts
1 of 40,475

The variety of compressions means developers can access a diverse range of deep architectures, quality metrics, and quality levels, and for the first time allows them to compare compressions on a commercially available device. Developers can either select pictures using their own device, or choose from curated images, and CompareAI’s slider-based mechanism lets them compare the quality of the images compressed using traditional techniques like JPEG and HEIC, with those that use new AI-based techniques. The app also offers a step-by-step interface, which helps developers better understand the compression process.

Recommended AI News: Givex Acquires Pi Cash Systeme in Switzerland

“The CompareAI app is a first on many fronts,” said Jean Bolot, Head of the AI Lab at InterDigital. “It propels image compression techniques forward by enabling deep-learning algorithms on resource-limited devices and can compare the quality obtained with traditional techniques. CompareAI improves the quality of image compression today, but also provides the groundwork for next generation techniques which will enable more high-quality images to be stored using much less space.”

Recommended AI News: Latest ezAccounting Software Offers Businesses Greater Security As Stand Alone Application

3 Comments
  1. Metal waste disposal regulations Ferrous material recycling buyback Iron recycling facility

    Ferrous material recycling process improvement, Iron recovery center, Metal reclaiming and repurposing

  2. Copper recycling company Copper scrap payment terms Scrap metal management solutions
    Copper cable collection, Automated metal sorting, Copper scrap circular economy

  3. Metal reprocessing and reclaiming Ferrous material plant operations Iron recycling and reclaiming

    Ferrous material demolition, Iron and steel scrapping, Scrap metal price fluctuations

Leave A Reply

Your email address will not be published.