Real time holography using learned error feedback
AssigneeIntel Corporation
InventorsAlexey Supikov, Qiong Huang, Ronald T. Azuma
Life of this patent
Estimating the term…
Abstract
Techniques related to generating holographic images are discussed. Such techniques include application of a pre-trained deep neural network to a target holographic image to generate a feedback strength value for error feedback in an iterative propagation feedback model and generating a diffraction pattern image corresponding to the target holographic image by applying the iterative propagation feedback model based on the target holographic image and using the feedback strength value.
Claims21
A system for generating holographic images comprising:
- a memory to store a target holographic image to be presented to a user at an image plane;
- and
- one or more processors coupled to the memory, the one or more processors to:
- apply a deep neural network to the target holographic image to generate a feedback strength value for error feedback in determination of a phase only diffraction pattern image using an iterative propagation feedback model, the phase only diffraction pattern image for presentation at a holographic plane to generate a corresponding holographic image at the image plane;
- apply the iterative propagation feedback model based on the target holographic image and using the feedback strength value to generate a final phase only diffraction pattern image for presentation at the holographic plane;
- and
- output the final diffraction pattern image for presentment at the holographic plane for generation of a corresponding final holographic image at the image plane.
A method for generating holographic images comprising:
- receiving a target holographic image to be presented to a user at an image plane;
- applying a deep neural network to the target holographic image to generate a feedback strength value for error feedback in determination of a phase only diffraction pattern image using an iterative propagation feedback model, the phase only diffraction pattern image for presentation at a holographic plane to generate a corresponding holographic image at the image plane;
- applying the iterative propagation feedback model based on the target holographic image and using the feedback strength value to generate a final phase only diffraction pattern image for presentation at the holographic plane;
- and
- presenting the final diffraction pattern image at the holographic plane to generate a corresponding final holographic image at the image plane.
At least one non-transitory machine readable medium comprising a plurality of instructions that, in response to being executed on a computing device, cause the computing device to generate holographic images by:
- receiving a target holographic image to be presented to a user at an image plane;
- applying a deep neural network to the target holographic image to generate a feedback strength value for error feedback in determination of a phase only diffraction pattern image using an iterative propagation feedback model, the phase only diffraction pattern image for presentation at a holographic plane to generate a corresponding holographic image at the image plane;
- applying the iterative propagation feedback model based on the target holographic image and using the feedback strength value to generate a final phase only diffraction pattern image for presentation at the holographic plane;
- and
- presenting the final diffraction pattern image at the holographic plane to generate a corresponding final holographic image at the image plane.
Dependencies are inferred from the claim text.