Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report

TL;DR

This paper presents deep learning-based ISP pipelines designed for mobile NPUs, achieving real-time performance and high image quality, developed as part of the Mobile AI 2021 challenge using a novel dataset.

Contribution

The paper introduces a new learned ISP dataset and demonstrates end-to-end deep learning models capable of replacing classical ISPs on mobile hardware.

Findings

Models process Full HD images in under 100 ms

Achieve high fidelity image quality

Compatible with mobile NPUs for real-time processing

Abstract

As the quality of mobile cameras starts to play a crucial role in modern smartphones, more and more attention is now being paid to ISP algorithms used to improve various perceptual aspects of mobile photos. In this Mobile AI challenge, the target was to develop an end-to-end deep learning-based image signal processing (ISP) pipeline that can replace classical hand-crafted ISPs and achieve nearly real-time performance on smartphone NPUs. For this, the participants were provided with a novel learned ISP dataset consisting of RAW-RGB image pairs captured with the Sony IMX586 Quad Bayer mobile sensor and a professional 102-megapixel medium format camera. The runtime of all models was evaluated on the MediaTek Dimensity 1000+ platform with a dedicated AI processing unit capable of accelerating both floating-point and quantized neural networks. The proposed solutions are fully compatible with the above NPU and are capable of processing Full HD photos under 60-100 milliseconds while achieving high fidelity results. A detailed description of all models developed in this challenge is provided in this paper.