AttentionLut: Attention Fusion-based Canonical Polyadic LUT for Real-time Image Enhancement
This addresses the problem of limited generalization in real-time image enhancement for applications like photography or video processing, representing an incremental improvement over existing LUT-based methods.
The paper tackled the limitation of linear combinations in image-adaptive lookup tables (LUTs) for real-time image enhancement by proposing AttentionLut, which uses an attention mechanism to generate image-adaptive LUTs, achieving better performance than state-of-the-art methods on the MIT-Adobe FiveK dataset.
Recently, many algorithms have employed image-adaptive lookup tables (LUTs) to achieve real-time image enhancement. Nonetheless, a prevailing trend among existing methods has been the employment of linear combinations of basic LUTs to formulate image-adaptive LUTs, which limits the generalization ability of these methods. To address this limitation, we propose a novel framework named AttentionLut for real-time image enhancement, which utilizes the attention mechanism to generate image-adaptive LUTs. Our proposed framework consists of three lightweight modules. We begin by employing the global image context feature module to extract image-adaptive features. Subsequently, the attention fusion module integrates the image feature with the priori attention feature obtained during training to generate image-adaptive canonical polyadic tensors. Finally, the canonical polyadic reconstruction module is deployed to reconstruct image-adaptive residual 3DLUT, which is subsequently utilized for enhancing input images. Experiments on the benchmark MIT-Adobe FiveK dataset demonstrate that the proposed method achieves better enhancement performance quantitatively and qualitatively than the state-of-the-art methods.