Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables

Recently, deep learning-based image enhancement algorithms achieved state-of-the-art (SOTA) performance on several publicly available datasets. However, most existing methods fail to meet practical requirements either for visual perception or for computation efficiency, especially for high-resolution images. In this paper, we propose a novel real-time image enhancer via learnable spatial-aware 3dimentional lookup tables(3D LUTs), which well considers global scenario and local spatial information. Specifically, we introduce a light weight two-head weight predictor that has two outputs. One is a 1D weight vector used for image-level scenario adaptation, the other is a 3D weight map aimed for pixel-wise category fusion. We learn the spatial-aware 3D LUTs and fuse them according to the aforementioned weights in an end-to-end manner. The fused LUT is then used to transform the source image into the target tone in an efficient way. Extensive results show that our model outperforms SOTA image enhancement methods on public datasets both subjectively and objectively, and that our model only takes about 4ms to process a 4K resolution image on one NVIDIA V100 GPU.

1. Introduction

Recently, many deep learning-based approaches have been proposed and achieved SOTA results [9], [15], [25], [4], [20], [14], [26], [19], [28] in the field of computational imaging. However, complex network architecture and high computation overheads prevent them from real-time processing. Figure 1 shows the comparison of performance and efficiency (i.e., execution time) of several network architectures on HDR+ Burst Photography dataset [6]. Most existing methods cannot produce visually pleasant results in real time.