Abstract
We present DeepISP, a full end-to-end deep neural model of the camera image signal processing pipeline. Our model learns a mapping from the raw low-light mosaiced image to the final visually compelling image and encompasses low-level tasks, such as demosaicing and denoising, as well as higher-level tasks, such as color correction and image adjustment. The training and evaluation of the pipeline were performed on a dedicated data set containing pairs of low-light and well-lit images captured by a Samsung S7 smartphone camera in both raw and processed JPEG formats. The proposed solution achieves the state-of-the-art performance in objective evaluation of peak signal-to-noise ratio on the subtask of joint denoising and demosaicing. For the full end-to-end pipeline, it achieves better visual quality compared to the manufacturer ISP, in both a subjective human assessment and when rated by a deep model trained for assessing image quality.
Original language | English |
---|---|
Article number | 8478390 |
Pages (from-to) | 912-923 |
Number of pages | 12 |
Journal | IEEE Transactions on Image Processing |
Volume | 28 |
Issue number | 2 |
DOIs | |
State | Published - Feb 2019 |
Keywords
- ISP
- Image processing
- color correction
- deep learning
- demosaicing
- denoising
All Science Journal Classification (ASJC) codes
- Software
- Computer Graphics and Computer-Aided Design