Principal Component Analysis-Based Terahertz Self-Supervised Denoising and Deblurring Deep Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908849462575104 |
|---|---|
| author | Zhu, Pengfei Sfarra, Stefano Zhang, Hai Santulli, Carlo Pivarciova, Elana Sarasini, Fabrizio Maldague, Xavier |
| author_facet | Zhu, Pengfei Sfarra, Stefano Zhang, Hai Santulli, Carlo Pivarciova, Elana Sarasini, Fabrizio Maldague, Xavier |
| contents | Terahertz (THz) systems inherently introduce frequency-dependent degradation effects, resulting in low-frequency blurring and high-frequency noise in amplitude images. Conventional image processing techniques cannot simultaneously address both issues, and manual intervention is often required due to the unknown boundary between denoising and deblurring. To tackle this challenge, we propose a principal component analysis (PCA)-based THz self-supervised denoising and deblurring network (THz-SSDD). The network employs a Recorrupted-to-Recorrupted self-supervised learning strategy to capture the intrinsic features of noise by exploiting invariance under repeated corruption. PCA decomposition and reconstruction are then applied to restore images across both low and high frequencies. The performance of the THz-SSDD network was evaluated on four types of samples. Training requires only a small set of unlabeled noisy images, and testing across samples with different material properties and measurement modes demonstrates effective denoising and deblurring. Quantitative analysis further validates the network feasibility, showing improvements in image quality while preserving the physical characteristics of the original signals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12149 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Principal Component Analysis-Based Terahertz Self-Supervised Denoising and Deblurring Deep Neural Networks Zhu, Pengfei Sfarra, Stefano Zhang, Hai Santulli, Carlo Pivarciova, Elana Sarasini, Fabrizio Maldague, Xavier Computer Vision and Pattern Recognition Terahertz (THz) systems inherently introduce frequency-dependent degradation effects, resulting in low-frequency blurring and high-frequency noise in amplitude images. Conventional image processing techniques cannot simultaneously address both issues, and manual intervention is often required due to the unknown boundary between denoising and deblurring. To tackle this challenge, we propose a principal component analysis (PCA)-based THz self-supervised denoising and deblurring network (THz-SSDD). The network employs a Recorrupted-to-Recorrupted self-supervised learning strategy to capture the intrinsic features of noise by exploiting invariance under repeated corruption. PCA decomposition and reconstruction are then applied to restore images across both low and high frequencies. The performance of the THz-SSDD network was evaluated on four types of samples. Training requires only a small set of unlabeled noisy images, and testing across samples with different material properties and measurement modes demonstrates effective denoising and deblurring. Quantitative analysis further validates the network feasibility, showing improvements in image quality while preserving the physical characteristics of the original signals. |
| title | Principal Component Analysis-Based Terahertz Self-Supervised Denoising and Deblurring Deep Neural Networks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.12149 |