AIM 2020 Challenge on Learned Image Signal Processing Pipeline
This work addresses the challenge of enhancing low-quality RAW images from mobile devices to match DSLR quality, which is incremental as it builds on existing ISP tasks.
The paper tackled the real-world RAW-to-RGB mapping problem by reviewing solutions from the AIM 2020 Challenge, where participants improved baseline results to set a new state-of-the-art for practical image signal processing pipelines.
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world RAW-to-RGB mapping problem, where to goal was to map the original low-quality RAW images captured by the Huawei P20 device to the same photos obtained with the Canon 5D DSLR camera. The considered task embraced a number of complex computer vision subtasks, such as image demosaicing, denoising, white balancing, color and contrast correction, demoireing, etc. The target metric used in this challenge combined fidelity scores (PSNR and SSIM) with solutions' perceptual results measured in a user study. The proposed solutions significantly improved the baseline results, defining the state-of-the-art for practical image signal processing pipeline modeling.