A method for MR virtual picture display based on a generative adversarial network

By establishing a display residual ledger in a generative adversarial network and setting nodes such as phase modulation and frequency modulation, the problems of anchor point drift, occlusion boundary misalignment, and unnatural lighting in MR virtual image display are solved, achieving a more stable and continuous virtual image display.

CN122368288APending Publication Date: 2026-07-10
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610800715.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Filing Date
2026-06-04
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing methods for displaying MR virtual images based on generative adversarial networks struggle to effectively address issues such as virtual image anchor point drift, misaligned occlusion boundaries, unnatural lighting blending, and continuous frame flickering.

Method used

By establishing a display residual ledger to record anchor point phase residuals, visibility residuals, illumination band residuals, and inter-frame phase residuals, and setting phase modulation, frequency modulation, visibility subtraction, frequency division subtraction, and phase wrap-around nodes in the SIREN generator, phase-locked propagation, visibility subtraction, illumination correction, and residual refeedback of virtual face elements are realized, thereby improving the continuity of the image.

Benefits of technology

It achieves spatial anchor point stability, occlusion accuracy, and image continuity in virtual images, reduces the drift of virtual elements relative to spatial anchor points, alleviates problems such as occlusion boundary misalignment and unnatural lighting blending, and improves the fusion consistency and continuous display effect of MR virtual images.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122368288A_ABST
    Figure CN122368288A_ABST
Patent Text Reader

Abstract

This invention discloses a method for displaying MR virtual images based on generative adversarial networks (GANs), comprising the following steps: constructing a display residual ledger, collecting anchor points, visibility, illumination, inter-frame residuals, and pose compensation; setting phase, frequency, visibility, frequency division, wraparound, and feedback nodes in the SIREN generator; modulating the phase and frequency terms with the anchor point phase residuals to form a phase-locked implicit state; generating an occlusion subtraction gate with the visibility residuals to correct inter-layer propagation; subtracting the illumination band residuals with frequency division to correct brightness and boundaries; wrapping the phase with the inter-frame phase residuals to form a continuous phase implicit state; decoding the surface element display record, identifying and feeding back the residuals, and stitching together to output the MR virtual image. This invention relates to the field of mixed reality display and artificial intelligence image generation technology, achieving stable display of MR virtual images and improving anchor point accuracy, occlusion fusion, and inter-frame continuity.
Need to check novelty before this filing date? Find Prior Art