Researchers from MIT, along with Holoeye’ s PLUTO-2.1 SLM, have figured out how to use AI in generating holograms that can run on a laptop. Presenting three-dimensional (3D) scenes that have continuous depth sensation has an extreme impact in the areas of virtual and augmented reality, training, education, and human computer interaction.
Tensor Holography synthesizes a 3D hologram with per-pixel depth from a single RGB-3D image in real-time as holography is making a big comeback thanks to AI in joining forces with deep learning that will enhance the virtual world experience.
For the holograms to be high quality, many data points require transference at high speeds. 5G promises high transfer rates soon, but deep learning assures the entire process can be efficient enough. The VR’s biggest challenge is its pressure on the user’s eye, as the illusions of 3D viewing of VR can result in nausea and eye strain. The solution for better 3D visualization lies within 60-year-old technology, remade for the digital world: holograms.
With 3D holograms being synthesized in real time, research done by Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT, the video of Big Buck Bunny shows a live capture from the HOLOEYE PLUTO 2.1 SLM. The camera focus is set on the eyes of the bunny, while the background of the trees is optically blurred due to camera defocus. Tensor holography needs a few seconds to craft holograms from images with depth information provided by typical computer-generated images and can be calculated from a multi-camera setup or LiDAR sensor. Since most smartphones come with LiDAR sensors, this work can help further research to bring real-time 3D holography and enable new applications in metasurface design, optical and acoustic tweezer-based microscopic manipulation, holographic microscopy, and single-exposure volumetric 3D printing.
Holoeye offers several different models of Spatial Light Modulators (SLM) for specific applications and needs.