Abstract
This work proposes a Covolutional Autoencoder based denoising method enhanced with morphological feature extraction to restore noisy Laguerre-Gaussian modes and achieves improved denoising performance, with an average PSNR of 43.56 dB, preserving essential structural features.
| Original language | English |
|---|---|
| Title of host publication | Signal Processing in Photonic Communications - Proceedings Advanced Photonics Congress 2025 |
| Publisher | Optical Society of America |
| ISBN (Electronic) | 9781957171517 |
| DOIs | |
| State | Published - 2025 |
| Event | 2025 Signal Processing in Photonic Communications, SPPCom 2025 - Marseille, France Duration: 13 Jul 2025 → 17 Jul 2025 |
Publication series
| Name | Signal Processing in Photonic Communications - Proceedings Advanced Photonics Congress 2025 |
|---|
Conference
| Conference | 2025 Signal Processing in Photonic Communications, SPPCom 2025 |
|---|---|
| Country/Territory | France |
| City | Marseille |
| Period | 13/07/25 → 17/07/25 |
Bibliographical note
Publisher Copyright:© 2025 Optica Publishing Group.
ASJC Scopus subject areas
- General Computer Science
- Space and Planetary Science
- Control and Systems Engineering
- Electrical and Electronic Engineering
- Electronic, Optical and Magnetic Materials
- Instrumentation
Fingerprint
Dive into the research topics of 'Machine Learning-Enhanced Denoising for Structured Light Modes in Realistic Optical Channels'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver