Exposure Interpolation by Combining Model-driven and Data-driven Methods
This work addresses image processing for applications like photography, but it is incremental as it fuses existing methods rather than introducing a new paradigm.
The paper tackles exposure interpolation by combining conventional and deep learning methods to generate medium exposure images from two large-exposure-ratio images, resulting in significantly increased image quality and improved convergence speed with reduced sample requirements.
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.