Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables
通过可学习的空间感知3D查找表实现实时图像增强
学習可能な空間意識3Dルックアップテーブルによる実時間画像エンハンサー
학습 가능 한 공간 감지 3D 를 통 해 표 의 실제 현실 을 찾 을 때 이미지 강화
Mejora de la imagen en tiempo real a través de la tabla de búsqueda 3D perceptiva espacial
Amélioration de l'image en temps réel à l'aide d'une table de recherche 3D sensible à l'espace
расширение изображений в реальном времени с помощью обучающейся таблицы пространственного восприятия 3D
Tao Wang 汪涛, Yong Li 李勇, Jingyang Peng 彭竞阳, Yipeng Ma 马翼鹏, Xian Wang 王宪, Fenglong Song 宋风龙, Youliang Yan 颜友亮
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 3-dimentional 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.
