Deep Neural Networks for HDR imaging
This work addresses image processing challenges for photography and computer vision applications, but appears incremental as it builds on existing neural network approaches.
The authors tackled HDR imaging by using Convolutional Neural Networks to generate HDR maps from LDR images and optimize tone mapping for improved TMQI scores, with quantitative performance demonstrated.
We propose novel methods of solving two tasks using Convolutional Neural Networks, firstly the task of generating HDR map of a static scene using differently exposed LDR images of the scene captured using conventional cameras and secondly the task of finding an optimal tone mapping operator that would give a better score on the TMQI metric compared to the existing methods. We quantitatively show the performance of our networks and illustrate the cases where our networks performs good as well as bad.