Neural‐Network–Enhanced Polarization‐Converted Metasurface Pixels for High‐Resolution, Crosstalk‐Free Full‐Color Augmented Reality Displays

ABSTRACT Environmentally friendly and highly stable metasurface color filters have significant potential for use in high‐resolution full‐color augmented reality (AR) near‐eye displays. However, their development is impeded by critical constraints, including a limited color gamut and notable background stray‐light interference. To address these problems, this paper proposes a high‐performance microdisplay scheme based on polarization‐converted metasurface pixels (PMPs) for high‐quality AR displays. The PMPs are fabricated using asymmetric cross‐shaped single‐crystal silicon metasurfaces on sapphire substrates. Under cross‐polarization, they transform incident white light into specific vivid colors and completely suppress light in non‐metasurface regions to eliminate background stray light, obviating the need for additional black matrix fabrication. To enhance color quality and grayscale diversity, a variational‐autoencoder–augmented neural network is utilized for inverse‐design optimization. Experimental findings indicate that the PMP‐based microdisplay attains a 105% sRGB color gamut, four distinct grayscale levels, and an ultrahigh resolution surpassing 46,000 dpi with a minimum pixel size of 550 nm. Patterned samples confirm the ability of the scheme to facilitate crosstalk‐free AR displays on which both real‐world scenes and displayed content can be clearly visualized. This study offers a novel and reliable approach for the advancement of next‐generation full‐color near‐eye display technologies.

Authors

Institutions

Publication Details

Journal
Advanced Optical Materials
Published
2026-07-24
DOI
https://doi.org/10.1002/adom.71478
Primary Topic
Metamaterials and Metasurfaces Applications
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Neural‐Network–Enhanced Polarization‐Converted Metasurface Pixels for High‐Resolution, Crosstalk‐Free Full‐Color Augmented Reality Displays

Xiongtu Zhou, Chaoxing Wu, Yuyan Peng, Weiquan Yang et al.
Advanced Optical Materials
Metamaterials and Metasurfaces Applications
article

Neural‐Network–Enhanced Polarization‐Converted Metasurface Pixels for High‐Resolution, Crosstalk‐Free Full‐Color Augmented Reality Displays

Xiongtu Zhou, Chaoxing Wu, Yuyan Peng, Weiquan Yang, J Zhang, Weipeng Lin, Yongai Zhang, Qun Yan, Zhenyou Zou, Tailiang Guo
article en

Abstract

ABSTRACT Environmentally friendly and highly stable metasurface color filters have significant potential for use in high‐resolution full‐color augmented reality (AR) near‐eye displays. However, their development is impeded by critical constraints, including a limited color gamut and notable background stray‐light interference. To address these problems, this paper proposes a high‐performance microdisplay scheme based on polarization‐converted metasurface pixels (PMPs) for high‐quality AR displays. The PMPs are fabricated using asymmetric cross‐shaped single‐crystal silicon metasurfaces on sapphire substrates. Under cross‐polarization, they transform incident white light into specific vivid colors and completely suppress light in non‐metasurface regions to eliminate background stray light, obviating the need for additional black matrix fabrication. To enhance color quality and grayscale diversity, a variational‐autoencoder–augmented neural network is utilized for inverse‐design optimization. Experimental findings indicate that the PMP‐based microdisplay attains a 105% sRGB color gamut, four distinct grayscale levels, and an ultrahigh resolution surpassing 46,000 dpi with a minimum pixel size of 550 nm. Patterned samples confirm the ability of the scheme to facilitate crosstalk‐free AR displays on which both real‐world scenes and displayed content can be clearly visualized. This study offers a novel and reliable approach for the advancement of next‐generation full‐color near‐eye display technologies.

Advanced Optical Materials
Tan Kah Kee Innovation Laboratory (CN), Fuzhou University (CN)
Life in Land
Openalex Percentile: Top 22%
Metamaterials and Metasurfaces Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.