Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Framework
This addresses a domain-specific problem for image fusion applications, offering a robust solution to handle degraded inputs without manual pre-enhancement steps, though it appears incremental as it builds on existing fusion methods with novel integration of VLMs.
The paper tackles the problem of infrared-visible image fusion in dual-source degraded scenarios, where existing methods struggle due to assumptions of high-quality inputs, and proposes GD^2Fusion, a framework integrating vision-language models for degradation perception with dual-domain optimization, achieving superior fusion performance compared to existing algorithms.
Most existing infrared-visible image fusion (IVIF) methods assume high-quality inputs, and therefore struggle to handle dual-source degraded scenarios, typically requiring manual selection and sequential application of multiple pre-enhancement steps. This decoupled pre-enhancement-to-fusion pipeline inevitably leads to error accumulation and performance degradation. To overcome these limitations, we propose Guided Dual-Domain Fusion (GD^2Fusion), a novel framework that synergistically integrates vision-language models (VLMs) for degradation perception with dual-domain (frequency/spatial) joint optimization. Concretely, the designed Guided Frequency Modality-Specific Extraction (GFMSE) module performs frequency-domain degradation perception and suppression and discriminatively extracts fusion-relevant sub-band features. Meanwhile, the Guided Spatial Modality-Aggregated Fusion (GSMAF) module carries out cross-modal degradation filtering and adaptive multi-source feature aggregation in the spatial domain to enhance modality complementarity and structural consistency. Extensive qualitative and quantitative experiments demonstrate that GD^2Fusion achieves superior fusion performance compared with existing algorithms and strategies in dual-source degraded scenarios. The code will be publicly released after acceptance of this paper.