Hierarchical Spatial-Frequency Aggregation for Spectral Deconvolution Imaging

2025-11-10

AI Summary

In spectral deconvolution imaging (SDI), reconstruction accuracy is hindered by scene-dependent composite convolution-integral operators, leading to poor prior integration and high computational overhead. To address these bottlenecks, this work proposes a hierarchical spatial-frequency aggregation unfolding framework—the first physics-informed deep unfolding architecture specifically designed for SDI. It reformulates the nonlinear inverse problem as a linear mapping via frequency-domain projection and introduces a novel spatial-frequency aggregation Transformer that explicitly fuses multi-domain priors in the frequency domain. By synergizing frequency-domain decomposition, iterative optimization, and cross-domain attention mechanisms, the method significantly improves reconstruction fidelity and generalizability. Experiments on both simulated and real-world SDI systems demonstrate state-of-the-art performance, achieving superior reconstruction quality while reducing memory and computational costs by over 30% compared to existing approaches.

Technology Category

• Computer Vision: Other Foundations of Computer Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Search and Optimization: Non-convex Optimization

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

Computational spectral imaging (CSI) achieves real-time hyperspectral imaging through co-designed optics and algorithms, but typical CSI methods suffer from a bulky footprint and limited fidelity. Therefore, Spectral Deconvolution imaging (SDI) methods based on PSF engineering have been proposed to achieve high-fidelity compact CSI design recently. However, the composite convolution-integration operations of SDI render the normal-equation coefficient matrix scene-dependent, which hampers the efficient exploitation of imaging priors and poses challenges for accurate reconstruction. To tackle the inherent data-dependent operators in SDI, we introduce a Hierarchical Spatial-Spectral Aggregation Unfolding Framework (HSFAUF). By decomposing subproblems and projecting them into the frequency domain, HSFAUF transforms nonlinear processes into linear mappings, thereby enabling efficient solutions. Furthermore, to integrate spatial-spectral priors during iterative refinement, we propose a Spatial-Frequency Aggregation Transformer (SFAT), which explicitly aggregates information across spatial and frequency domains. By integrating SFAT into HSFAUF, we develop a Transformer-based deep unfolding method, extbf{H}ierarchical extbf{S}patial- extbf{F}requency extbf{A}ggregation extbf{U}nfolding extbf{T}ransformer (HSFAUT), to solve the inverse problem of SDI. Systematic simulated and real experiments show that HSFAUT surpasses SOTA methods with cheaper memory and computational costs, while exhibiting optimal performance on different SDI systems.

Problem

• SDI methods have scene-dependent coefficient matrices
• Existing approaches struggle with efficient prior exploitation
• Accurate spectral reconstruction faces computational challenges

Innovation

• Hierarchical framework transforms nonlinear processes into linear mappings
• Spatial-Frequency Aggregation Transformer integrates cross-domain priors
• Transformer-based deep unfolding solves inverse problem efficiently