Optimization-Based Data Generation for Photo Enhancement
Optimization-Based Data Generation for Photo Enhancement
复制标题
DOI：
10.1109/cvprw.2019.00240
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Mayu Omiya;Yusuke Horiuchi;E. Simo-Serra;S. Iizuka;H. Ishikawa
中科院分区：
文献类型：
--
作者：
Mayu Omiya;Yusuke Horiuchi;E. Simo-Serra;S. Iizuka;H. Ishikawa
大量高质量训练数据的准备一直是制约监督学习方法性能的瓶颈。对于像照片增强这样复杂的任务，它特别耗时。最近一种简化数据注释的方法通过优化自动创建真实的训练数据。在本文中，我们通过学习图像相似度来改进这种方法，该方法与协方差矩阵自适应优化方法相结合，使我们能够创建更高质量的训练数据来增强照片。我们通过进行感知用户研究来评估我们的方法对现实世界照片增强图像的挑战，这表明它的性能优于现有的方法。
The preparation of large amounts of high-quality training data has always been the bottleneck for the performance of supervised learning methods. It is especially time-consuming for complicated tasks such as photo enhancement. A recent approach to ease data annotation creates realistic training data automatically with optimization. In this paper, we improve upon this approach by learning image-similarity which, in combination with a Covariance Matrix Adaptation optimization method, allows us to create higher quality training data for enhancing photos. We evaluate our approach on challenging real world photo-enhancement images by conducting a perceptual user study, which shows that its performance compares favorably with existing approaches.