Main article: Neural networks (neural networks)
2024: Development of a neural network for the calculation and synthesis of holographic images
Employees of the Laboratory of Photonics and Optical Information Processing NRNU MEPhI have developed an original neural network for calculating and synthesizing holographic images. The university announced this on December 10, 2024.
| The speed of calculating high-quality holograms by "conventional" methods is low, "says a laboratory employee, Dmitry Rymov. - We have developed a method that uses the neural network of the original architecture and a branched structure to take into account a large set of sections of a three-dimensional scene in a calculated hologram. The network is trained on samples ranging from tens of thousands to hundreds of thousands of examples. The method was successfully used in experiments in the optical formation of three-dimensional scenes, in the implementation of holograms using high-resolution high-speed space-time light modulators of the latest types.
|
|
| The use of computer-synthesized holograms is promising in the creation of three-dimensional imaging tools, for laser control of microparticles, in photostimulation of biological neurons, for 3D printing, in the transformation and focusing of light beams, in the construction of holographic memory systems and much more - explained Rostislav Starikov.
|
|
| The use of neural networks makes it possible to calculate or, more precisely, generate a hologram if the network is previously successfully trained. Training takes time and large training samples, but a trained network generates a hologram very quickly, says the head of the laboratory.
|
|
| Intelligent methods make it possible to significantly expand the boundaries of the possibilities of using neural networks when solving not only amateur problems, but also when using them to solve problems in complex scientific topics, "said Pavel Cheremkhin, associate professor of the Department of Laser Physics at NRNU MEPhI. So, in just a couple of years, we have achieved such a high quality of calculations of holograms by neural network methods that it exceeds some capabilities of standard methods that have developed for decades. Our lab has developed a method that synthesizes megapixel holograms of complex 3D scenes in just a fraction of a second. At the same time, a high level of optical reproduction quality of these 3D scenes from such holograms has been achieved. And the use for the implementation of space-time light modulators allows you to form thousands of holograms per second and, accordingly, change or transform the three-dimensional light distribution thousands of times per second.
|
|