Total Variation Subgradient Guided Image Fusion for Dual-Camera CASSI System

2025-09-13

AI Summary

Spectral imaging has long suffered from fundamental trade-offs among spectral, spatial, and temporal resolution; while compressive coded aperture snapshot spectral imaging (CASSI) alleviates this tension, high compression ratios render reconstruction ill-posed. To address this, we propose a dual-camera CASSI (SD-CASSI) reconstruction framework that innovatively integrates total variation (TV) subgradient theory with spatial priors from an auxiliary RGB or panchromatic camera, yielding an end-to-end interpretable mathematical model. We design a TV subgradient similarity function and an adaptive reference generation mechanism, jointly incorporating normalized gradient constraints and the alternating direction method of multipliers (ADMM) for optimization—guaranteeing strict convexity and physical interpretability. Experiments demonstrate substantial improvements in spatial-spectral structural consistency and robustness under varying noise and sampling conditions. The implementation is publicly available.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

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: Assisted, interactive, and conversational search
• Security and Privacy: Data transparency and provenance

Abstract

Spectral imaging technology has long-faced fundamental challenges in balancing spectral, spatial, and temporal resolutions. While compressive sensing-based Coded Aperture Snapshot Spectral Imaging (CASSI) mitigates this trade-off through optical encoding, high compression ratios result in ill-posed reconstruction problems. Traditional model-based methods exhibit limited performance due to reliance on handcrafted inherent image priors, while deep learning approaches are constrained by their black-box nature, which compromises physical interpretability. To address these limitations, we propose a dual-camera CASSI reconstruction framework that integrates total variation (TV) subgradient theory. By establishing an end-to-end SD-CASSI mathematical model, we reduce the computational complexity of solving the inverse problem and provide a mathematically well-founded framework for analyzing multi-camera systems. A dynamic regularization strategy is introduced, incorporating normalized gradient constraints from RGB/panchromatic-derived reference images, which constructs a TV subgradient similarity function with strict convex optimization guarantees. Leveraging spatial priors from auxiliary cameras, an adaptive reference generation and updating mechanism is designed to provide subgradient guidance. Experimental results demonstrate that the proposed method effectively preserves spatial-spectral structural consistency. The theoretical framework establishes an interpretable mathematical foundation for computational spectral imaging, demonstrating robust performance across diverse reconstruction scenarios. The source code is available at https://github.com/bestwishes43/ADMM-TVDS.

Problem

• Balancing spectral, spatial, temporal resolutions in spectral imaging
• Solving ill-posed reconstruction problems in compressed CASSI systems
• Integrating mathematical interpretability with deep learning reconstruction

Innovation

• Integrates total variation subgradient theory mathematically
• Uses dual-camera spatial priors for adaptive guidance
• Establishes interpretable end-to-end reconstruction framework