MESSFN : a Multi-level and Enhanced Spectral-Spatial Fusion Network for Pan-sharpening

TL;DR

The paper introduces MESSFN, a novel multi-level spectral-spatial fusion network for pan-sharpening that leverages hierarchical fusion and specialized attention blocks to improve image fusion quality.

Contribution

It proposes a hierarchical multi-level fusion architecture with spectral-spatial streams and novel attention blocks, enhancing spectral and spatial feature extraction for better pan-sharpening.

Findings

Outperforms state-of-the-art methods on two datasets

Demonstrates superior spectral and spatial feature fusion

Achieves competitive or better fusion quality

Abstract

Dominant pan-sharpening frameworks simply concatenate the MS stream and the PAN stream once at a specific level. This way of fusion neglects the multi-level spectral-spatial correlation between the two streams, which is vital to improving the fusion performance. In consideration of this, we propose a Multi-level and Enhanced Spectral-Spatial Fusion Network (MESSFN) with the following innovations: First, to fully exploit and strengthen the above correlation, a Hierarchical Multi-level Fusion Architecture (HMFA) is carefully designed. A novel Spectral-Spatial (SS) stream is established to hierarchically derive and fuse the multi-level prior spectral and spatial expertise from the MS stream and the PAN stream. This helps the SS stream master a joint spectral-spatial representation in the hierarchical network for better modeling the fusion relationship. Second, to provide superior expertise, consequently, based on the intrinsic characteristics of the MS image and the PAN image, two feature extraction blocks are specially developed. In the MS stream, a Residual Spectral Attention Block (RSAB) is proposed to mine the potential spectral correlations between different spectra of the MS image through adjacent cross-spectrum interaction. While in the PAN stream, a Residual Multi-scale Spatial Attention Block (RMSAB) is proposed to capture multi-scale information and reconstruct precise high-frequency details from the PAN image through an improved spatial attention-based inception structure. The spectral and spatial feature representations are enhanced. Extensive experiments on two datasets demonstrate that the proposed network is competitive with or better than state-of-the-art methods. Our code can be found in github.