Brighten up Images via Dual-Branch Structure-Texture Awareness Feature Interaction

Images captured under low-light conditions suffer from inevitable degradation leading to the missing global structure and detailed local texture. However, existing methods consider these two components as a single entity or perform a similar convolutional operation, which can yield suboptimal results. In this letter, we propose a dual-branch structure-texture awareness feature interaction network named DFINet to tackle the above problems. First, we generate structure and texture components through the Gaussian operator. Subsequently, we conduct CNN-based and Transformer-based branches to cope with the texture and structure components separately. Among them, we design a Feature Interaction Block that leverages local-global information to enrich features in the encoding phase. Then, we generate queries with the potential structural-texture cues for the Transformer blocks in the decoding phase. Finally, we develop a Fusion Block to progressively integrate cross-layer features from two branches for the reconstruction. Our extensive experiment indicates the proposed method outperforms several representative methods in terms of both visual quality and objective assessment.