Learned Lightweight Smartphone ISP with Unpaired Data

TL;DR

This paper introduces a novel unpaired training method for lightweight smartphone image signal processing that eliminates the need for pixel-wise aligned data, enabling high-quality image reconstruction using adversarial learning and pre-trained feature discriminators.

Contribution

It proposes a new unpaired learning approach for lightweight smartphone ISP that removes the requirement for paired training data, leveraging adversarial training with multiple discriminators.

Findings

Achieves high fidelity image reconstruction comparable to paired methods

Uses lightweight neural networks suitable for mobile devices

Demonstrates effectiveness on Zurich RAW to RGB and Fujifilm UltraISP datasets

Abstract

The Image Signal Processor (ISP) is a fundamental component in modern smartphone cameras responsible for conversion of RAW sensor image data to RGB images with a strong focus on perceptual quality. Recent work highlights the potential of deep learning approaches and their ability to capture details with a quality increasingly close to that of professional cameras. A difficult and costly step when developing a learned ISP is the acquisition of pixel-wise aligned paired data that maps the raw captured by a smartphone camera sensor to high-quality reference images. In this work, we address this challenge by proposing a novel training method for a learnable ISP that eliminates the need for direct correspondences between raw images and ground-truth data with matching content. Our unpaired approach employs a multi-term loss function guided by adversarial training with multiple discriminators processing feature maps from pre-trained networks to maintain content structure while learning color and texture characteristics from the target RGB dataset. Using lightweight neural network architectures suitable for mobile devices as backbones, we evaluated our method on the Zurich RAW to RGB and Fujifilm UltraISP datasets. Compared to paired training methods, our unpaired learning strategy shows strong potential and achieves high fidelity across multiple evaluation metrics. The code and pre-trained models are available at https://github.com/AndreiiArhire/Learned-Lightweight-Smartphone-ISP-with-Unpaired-Data .