PQDynamicISP: Dynamically Controlled Image Signal Processor for Any Image Sensors Pursuing Perceptual Quality
This addresses the need for efficient and adaptable ISPs for image processing, offering a solution that works across different sensors without retraining, though it is incremental as it builds on conventional ISP functions.
The paper tackles the problem of improving image quality in image signal processors (ISPs) by proposing a lightweight ISP that dynamically controls parameters for each environment and locally, achieving state-of-the-art accuracy on various datasets and tasks while being lighter than DNN-based ISPs.
Full DNN-based image signal processors (ISPs) have been actively studied and have achieved superior image quality compared to conventional ISPs. In contrast to this trend, we propose a lightweight ISP that consists of simple conventional ISP functions but achieves high image quality by increasing expressiveness. Specifically, instead of tuning the parameters of the ISP, we propose to control them dynamically for each environment and even locally. As a result, state-of-the-art accuracy is achieved on various datasets, including other tasks like tone mapping and image enhancement, even though ours is lighter than DNN-based ISPs. Additionally, our method can process different image sensors with a single ISP through dynamic control, whereas conventional methods require training for each sensor.