Toward a Unified Dual-Path Framework for Multimodal Remote Sensing Data Fusion: Integrating Temporal, Resolution, and Spectral Dimensions

Remote sensing image fusion integrates observations from multiple sensors, spectral domains, and temporal acquisitions to exploit complementary and differential information, thereby producing more complete, consistent, and analytically valuable representations of the Earth system. However, existing fusion approaches are predominantly designed for specific tasks or modalities, which restrict their generalization and scalability. To this end, we propose a fusion network with dual-path learning strategy (DPLNet) that provides a unified framework for three fusion tasks: spatiotemporal fusion, change detection, and pan-sharpening. DPLNet comprises two primary stages: Feature extraction (FE) stage and multiscale feature fusion (MFF) stage. In the FE stage, the two remote sensing images are independently processed through one stream of the dual-path encoder. Subsequently, in the MFF stage, all multiscale features are adaptively integrated within a unified fusion module, where features from corresponding scales are fused adaptively without predefined task-specific interaction rules, allowing the model to learn cross-source feature relationships in a data-driven manner for final prediction. Experiments on multiple datasets demonstrate that DPLNet achieves state-of-the-art performance, consistently surpassing specialized models in both quantitative accuracy and qualitative comparison. These results highlight the potential of DPLNet as a task-general framework for representative optical remote sensing fusion tasks, offering a scalable and efficient solution for Earth observation.