The paper “Learned Lightweight Smartphone ISP with Unpaired Data” introduces a novel training method for a learnable Image Signal Processor (ISP) that eliminates the need for paired data, which are difficult and costly to acquire. The approach employs a multi-term loss function guided by adversarial training with multiple discriminators processing feature maps from pre-trained networks. The goal is to maintain content structure while learning color and texture characteristics from the target RGB dataset. The method uses lightweight neural network architectures suitable for mobile devices and is evaluated on the Zurich RAW to RGB and Fujifilm UltraISP datasets.