DeepISP: Learning End-to-End Image Processing Pipeline

Eli Schwartz, Raja Giryes, Alex M. Bronstein

Feb 11, 2018 (modified: Feb 11, 2018) ICLR 2018 Workshop Submission readers: everyone
  • Abstract: We present DeepISP, a full end-to-end deep neural model of the camera image signal processing (ISP) 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 dataset, the S7-ISP dataset, 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 state-of-the-art performance in objective evaluation of PSNR 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.
  • TL;DR: First to show learning of the full image processing pipeline end-to-end. SOTA results for joint denoising and demosaicing.
  • Keywords: deep learning, ISP, image processing, denoising, demosaicing, s7-isp, deepisp