Principal Component Analysis-Based Terahertz Self-Supervised Denoising and Deblurring Deep Neural Networks

TL;DR

This paper introduces a PCA-based self-supervised neural network for simultaneous denoising and deblurring of terahertz images, effectively handling frequency-dependent degradation with minimal labeled data.

Contribution

It presents a novel self-supervised learning approach combining PCA and Recorrupted-to-Recorrupted strategy for THz image restoration, requiring only unlabeled data.

Findings

Effective noise reduction and image restoration demonstrated across multiple sample types.

Requires only a small set of unlabeled noisy images for training.

Quantitative results show significant improvement in image quality while preserving physical signal characteristics.

Abstract

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.