Incorporating a world-class AI research team from Technicolor, InterDigital’s Artificial Intelligence (AI) Lab specializes in infusing next generation wireless and immersive experiences with the latest advancements in AI, while exploring how to apply these capabilities in the home and beyond.
InterDigital harnesses the deep-learning revolution to build novel services and cognitive apps on resource-constrained devices such as OTT boxes and IoT devices, including transparently monitoring user interactions with OTT services to analyze interests and personalize the user experience.
InterDigital Artificial Intelligence Lab transforms large-scale workflow and asset data collected during VFX production into business insights by creating predictive analytics to accurately forecast artist and computing resources, improve VFX production performance, and optimize digital asset lifecycles.
The InterDigital Artificial Intelligence Lab specializes in adapting and applying the latest advances in Artificial Intelligence (AI) to the creation and delivery of next-generation content – and in innovating how these advances can be applied at home for the benefit of consumers everywhere.
This easy-to-use iOS app enables the use of state-of-the-art Deep Learning-based image compression algorithms on a resource-constrained device. CompareAI features a Deep Learning-based image encoder, a decoder, and an entropy coder to generate bitstreams comparable to traditional image compression algorithms.
Emerging applications for AI and deep learning outline the significant need to optimize energy efficiency to improve battery use, extend battery life, and promote sustainability. Energy considerations have become crucial to the success of AI for wireless, and InterDigital continues to research and develop cutting edge techniques to measure and optimize the energy use of deep neural networks (DNN) to increase battery life or expedite inference.
Efficient video compression is critical for the storage and transmission of growing video content, especially as deep learning-based approaches have quickly exceeded traditional approaches for image compression. InterDigital is a leader in the design of disruptive video codecs based on deep learning techniques to complement ongoing augmentation of modules in existing software codec architectures, providing a natural way to represent video content using latent representations and offering a solution especially suited for interpretation by other neural networks or machines, like IoT devices.
InterDigital is dedicated to developing neural network-based models that achieve better performance and using neural networks to address the complex optimization problems that arise in wireless system design for 5G and beyond. Our engineers lead research to optimize wireless systems, particularly when the channel state is highly dynamic and channel state information (CSI) varies over time and location. Deep neural networks help approximate the otherwise unknown input and output of wireless optimization problems, enabling inference to be done in quasi-real-time.
The promise and rapid growth of cloud gaming has unveiled the need to automate the process of generating gaming content. InterDigital addresses the particular technical challenges related to the creation and tuning of 3D assets based on a text description, including the initial creation of the asset from a text avatar and the tuning or personalization of the avatar based on user feedback, enabling users to have more input into the creative process.
learn more about artificial intelligence labs
