Immersive Lab

Today’s solutions for tomorrow’s interactive media environment.
  • overview
  • research topics
  • get started
Immersive logo - VR goggles

InterDigital’s Immersive Lab develops today’s solutions for tomorrow’s interactive media environment. Through the application of innovations in computer graphics, computer vision, video processing, deep learning and optics, we offer professionals and end-users alike the solutions they need to amplify their immersive experiences. Research areas focuses on:

  • Mixed Reality
  • Virtual Production and Real-Time Content
  • Deep Content Generation
  • Volumetric Imaging Technologies

Research Topics

Deep Content Generation

Deep Learning and Synthetic Content are two technologies to create a new media for the e-society to communicate, train, share, play, discover and live. The goal of this research area is to explore the deep generated imaging (DGI) field and particularly how to generate realistic and evolutionary environments and characters, learn personalized models animated and responsive to the environment, use artificial emotional intelligence to humanize interaction between real and virtual individuals and render content for a natural user experience.

Virtual Production & Real-Time Content

The alliance between movie and game industries has progressively happened, bringing more real-time tools to traditional VFX workflows, while pushing the expected level of rendering quality in gaming. It impacts the full creation and distribution pipeline, and the final media itself which will evolve towards more immersion, interactivity, realism, and with new paradigms. This research area address two main tracks: creating high quality interactive Digital Humans (avatars), and pushing the boundaries of real-time content and tools.

Mixed Reality

The goal of this research area is to propose technologies and workflows enabling context-aware mixed -reality experiences and visual personalization of the real-world environment. More particularly, our research activities focus on scene analysis and modeling, camera pose estimation and device localization, as well as high-performance graphics rendering on mobile devices.

Volumetric Imaging & Light Guiding

The Volumetric Imaging research area addresses the future of video experiences through data processing, data formatting, and product engineering device technologies. Volumetric Video allows the user to get the sensation of depth and parallax both with synthetic and real content.

The Volumetric Video technologies include Light field capture and processing pipeline to create multi-views + depth volumetric content. The associated Volumetric Video format technologies contribute to the MPEG 3VC-MIV standard to distribute and render volumetric video content. The Volumetric Video rendering techniques are key to address new use cases and to adapt content to any device from 2D displays, VR HMD and multi-views/light field displays and AR glasses. Future work in this research area includes digital holography techniques to generate digital holograms and provide future video formats for digital hologram distribution.

This new trend requires innovation in product engineering device technologies. For that, we develop light guiding technologies for future optical components for use in AR glasses and image sensors.

get started

learn more about immersive labs