Hybrid Frequency–Spatial Domain Learning for Image Restoration in Under-Display Camera Systems Using Augmented Virtual Big Data Generated by the Angular Spectrum Method
In the rapidly advancing realm of mobile technology, under-display camera (UDC) systems have emerged as a promising solution for achieving seamless full-screen displays. Despite their innovative potential, UDC systems face significant challenges, including low light transmittance and pronounced diff...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/1/30 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549505835565056 |
|---|---|
| author | Kibaek Kim Yoon Kim Young-Joo Kim |
| author_facet | Kibaek Kim Yoon Kim Young-Joo Kim |
| author_sort | Kibaek Kim |
| collection | DOAJ |
| description | In the rapidly advancing realm of mobile technology, under-display camera (UDC) systems have emerged as a promising solution for achieving seamless full-screen displays. Despite their innovative potential, UDC systems face significant challenges, including low light transmittance and pronounced diffraction effects that degrade image quality. This study aims to address these issues by examining degradation phenomena through optical simulation and employing a deep neural network model incorporating hybrid frequency–spatial domain learning. To effectively train the model, we generated a substantial synthetic dataset that virtually simulates the unique image degradation characteristics of UDC systems, utilizing the angular spectrum method for optical simulation. This approach enabled the creation of a diverse and comprehensive dataset of virtual degraded images by accurately replicating the degradation process from pristine images. The augmented virtual data were combined with actual degraded images as training data, compensating for the limitations of real data availability. Through our proposed methods, we achieved a marked improvement in image quality, with the average structural similarity index measure (SSIM) value increasing from 0.8047 to 0.9608 and the peak signal-to-noise ratio (PSNR) improving from 26.383 dB to 36.046 dB on an experimentally degraded image dataset. These results highlight the potential of our integrated optics and AI-based methodology in addressing image restoration challenges within UDC systems and advancing the quality of display technology in smartphones. |
| format | Article |
| id | doaj-art-67bf3601dab14241aecda80adba02761 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-67bf3601dab14241aecda80adba027612025-01-10T13:14:12ZengMDPI AGApplied Sciences2076-34172024-12-011513010.3390/app15010030Hybrid Frequency–Spatial Domain Learning for Image Restoration in Under-Display Camera Systems Using Augmented Virtual Big Data Generated by the Angular Spectrum MethodKibaek Kim0Yoon Kim1Young-Joo Kim2Department of Mechanical Engineering, Yonsei University, Seoul 03722, Republic of KoreaDepartment of Mechanical Engineering, Yonsei University, Seoul 03722, Republic of KoreaDepartment of Mechanical Engineering, Yonsei University, Seoul 03722, Republic of KoreaIn the rapidly advancing realm of mobile technology, under-display camera (UDC) systems have emerged as a promising solution for achieving seamless full-screen displays. Despite their innovative potential, UDC systems face significant challenges, including low light transmittance and pronounced diffraction effects that degrade image quality. This study aims to address these issues by examining degradation phenomena through optical simulation and employing a deep neural network model incorporating hybrid frequency–spatial domain learning. To effectively train the model, we generated a substantial synthetic dataset that virtually simulates the unique image degradation characteristics of UDC systems, utilizing the angular spectrum method for optical simulation. This approach enabled the creation of a diverse and comprehensive dataset of virtual degraded images by accurately replicating the degradation process from pristine images. The augmented virtual data were combined with actual degraded images as training data, compensating for the limitations of real data availability. Through our proposed methods, we achieved a marked improvement in image quality, with the average structural similarity index measure (SSIM) value increasing from 0.8047 to 0.9608 and the peak signal-to-noise ratio (PSNR) improving from 26.383 dB to 36.046 dB on an experimentally degraded image dataset. These results highlight the potential of our integrated optics and AI-based methodology in addressing image restoration challenges within UDC systems and advancing the quality of display technology in smartphones.https://www.mdpi.com/2076-3417/15/1/30under-display camerahybrid frequency–spatial domain learningdeep neural networkimage restorationangular spectrum methodvirtual big data |
| spellingShingle | Kibaek Kim Yoon Kim Young-Joo Kim Hybrid Frequency–Spatial Domain Learning for Image Restoration in Under-Display Camera Systems Using Augmented Virtual Big Data Generated by the Angular Spectrum Method Applied Sciences under-display camera hybrid frequency–spatial domain learning deep neural network image restoration angular spectrum method virtual big data |
| title | Hybrid Frequency–Spatial Domain Learning for Image Restoration in Under-Display Camera Systems Using Augmented Virtual Big Data Generated by the Angular Spectrum Method |
| title_full | Hybrid Frequency–Spatial Domain Learning for Image Restoration in Under-Display Camera Systems Using Augmented Virtual Big Data Generated by the Angular Spectrum Method |
| title_fullStr | Hybrid Frequency–Spatial Domain Learning for Image Restoration in Under-Display Camera Systems Using Augmented Virtual Big Data Generated by the Angular Spectrum Method |
| title_full_unstemmed | Hybrid Frequency–Spatial Domain Learning for Image Restoration in Under-Display Camera Systems Using Augmented Virtual Big Data Generated by the Angular Spectrum Method |
| title_short | Hybrid Frequency–Spatial Domain Learning for Image Restoration in Under-Display Camera Systems Using Augmented Virtual Big Data Generated by the Angular Spectrum Method |
| title_sort | hybrid frequency spatial domain learning for image restoration in under display camera systems using augmented virtual big data generated by the angular spectrum method |
| topic | under-display camera hybrid frequency–spatial domain learning deep neural network image restoration angular spectrum method virtual big data |
| url | https://www.mdpi.com/2076-3417/15/1/30 |
| work_keys_str_mv | AT kibaekkim hybridfrequencyspatialdomainlearningforimagerestorationinunderdisplaycamerasystemsusingaugmentedvirtualbigdatageneratedbytheangularspectrummethod AT yoonkim hybridfrequencyspatialdomainlearningforimagerestorationinunderdisplaycamerasystemsusingaugmentedvirtualbigdatageneratedbytheangularspectrummethod AT youngjookim hybridfrequencyspatialdomainlearningforimagerestorationinunderdisplaycamerasystemsusingaugmentedvirtualbigdatageneratedbytheangularspectrummethod |