Fourier-Modulated Implicit Neural Representation for Multispectral Satellite Image Compression

2025/06/02 by Woojin Cho, Steve Andreas Immanuel, Cho, Woojin +5
Computer Science · #Advanced Computational Techniques and Applications #Advanced Data Compression Techniques #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Signal Denoising Methods #Image and Video Processing (eess.IV) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2506.01234

openalex publication_date 2025/06/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Multispectral satellite images play a vital role in agriculture, fisheries, and environmental monitoring. However, their high dimensionality, large data volumes, and diverse spatial resolutions across multiple channels pose significant challenges for data compression and analysis. This paper presents ImpliSat, a unified framework specifically designed to address these challenges through efficient compression and reconstruction of multispectral satellite data. ImpliSat leverages Implicit Neural Representations (INR) to model satellite images as continuous functions over coordinate space, capturing fine spatial details across varying spatial resolutions. Furthermore, we introduce a Fourier modulation algorithm that dynamically adjusts to the spectral and spatial characteristics of each band, ensuring optimal compression while preserving critical image details.

Citations

• Neural Functions for Learning Periodic Signal
• Unveiling the Potential of Superexpressive Networks in Implicit Neural Representations
• FastLRNR and Sparse Physics Informed Backpropagation
• Improved Implicit Neural Representation with Fourier Reparameterized Training
• Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks
• Spatial Functa: Scaling Functa to ImageNet Classification and Generation
• COIN++: Neural Compression Across Modalities
• From data to functa: Your data point is a function and you can treat it like one
• Implicit Neural Representations for Image Compression
• LoRA: Low-Rank Adaptation of Large Language Models
• D-NeRF: Neural Radiance Fields for Dynamic Scenes
• Implicit Neural Representations with Periodic Activation Functions
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Adam: A Method for Stochastic Optimization
• The JPEG still picture compression standard

Related

• Hyperspectral Image Compression Using Implicit Neural Representation
• Mixed-granularity Implicit Representation for Continuous Hyperspectral Compressive Reconstruction
• Hyperspectral Image Compression Using Sampling and Implicit Neural Representations
• SatSynthBurst
• FusionRF: High-Fidelity Satellite Neural Radiance Fields from Multispectral and Panchromatic Acquisitions