Deep learning based methods have penetrated many image processing problems and become dominant solutions to these problems. A natural question raised here is "Is there any space for conventional methods on these problems?" In this paper, exposure interpolation is taken as an example to answer this question and the answer is "Yes". A framework on fusing conventional and deep learning method is introduced to generate an medium exposure image for two large-exposureratio images. Experimental results indicate that the quality of the medium exposure image is increased significantly through using the deep learning method to refine the interpolated image via the conventional method. The conventional method can be adopted to improve the convergence speed of the deep learning method and to reduce the number of samples which is required by the deep learning method.
翻译:基于深层学习的方法已渗透到许多图像处理问题,并成为这些问题的主要解决办法。在这里提出的一个自然问题是,“在这些问题上是否有常规方法的空间?”在本文件中,将接触内插作为回答这一问题的范例,答案是“是的”。引入了一个关于使用常规和深层学习方法的框架,为两种大接触图像生成中度暴露图像。实验结果表明,通过使用深层学习方法通过常规方法改进内插图像,中度暴露图像的质量得到显著提高。可以采用传统方法提高深层学习方法的趋同速度,并减少深层学习方法所需的样本数量。