Structure Modeling Activation Free Fourier Network for Spacecraft Image Denoising

2024-09-11

AI Summary

To address the degradation of existing deep denoising methods on spacecraft imagery—characterized by low illumination and strong periodic structural patterns—this paper proposes a synergistic architecture integrating structural modeling and activation-free Fourier-domain processing. Our method introduces two key innovations: (1) a Structural Modeling Block (SMB) that enhances edge and local structural representation; and (2) an Activation-Free Fourier Block (AFFB), which leverages a modified Fast Fourier Transform (FFT) combined with lightweight convolutions to capture long-range periodic features and enable linear frequency-domain modeling. The architecture jointly optimizes dark-region detail recovery and global structural consistency. Evaluated on a custom spacecraft noise dataset, it surpasses state-of-the-art methods by over 1.27 dB in PSNR. The implementation is publicly available, demonstrating effectiveness, computational efficiency, and engineering practicality.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: Diffusion Models for Vision
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

Spacecraft image denoising is a crucial fundamental technology closely related to aerospace research. However, the existing deep learning-based image denoising methods are primarily designed for natural image and fail to adequately consider the characteristics of spacecraft image(e.g. low-light conditions, repetitive periodic structures), resulting in suboptimal performance in the spacecraft image denoising task. To address the aforementioned problems, we propose a Structure modeling Activation Free Fourier Network (SAFFN), which is an efficient spacecraft image denoising method including Structure Modeling Block (SMB) and Activation Free Fourier Block (AFFB). We present SMB to effectively extract edge information and model the structure for better identification of spacecraft components from dark regions in spacecraft noise image. We present AFFB and utilize an improved Fast Fourier block to extract repetitive periodic features and long-range information in noisy spacecraft image. Extensive experimental results demonstrate that our SAFFN performs competitively compared to the state-of-the-art methods on spacecraft noise image datasets. The codes are available at: https://github.com/shenduke/SAFFN.

Problem

• Denoising spacecraft images with unique characteristics
• Addressing low-light and repetitive structure challenges
• Improving edge and periodic feature extraction

Innovation

• Structure Modeling Block extracts edge information
• Activation Free Fourier Block captures periodic features
• Improved Fast Fourier block processes long-range information