Flexible High‐Speed Low‐Noise Organic Photodiode Arrays for Dynamic Near‐Infrared Imaging

ABSTRACT Organic photodiodes (OPDs) hold significant promise for next‐generation IoT optical sensing and low‐power imaging applications. However, widespread application of OPD in flexible and dynamic imaging has been constrained by high dark current, poor stability, and the lack of a cost‐effective imaging system. In this work, we present an integrated solution through tailoring pseudo‐planar heterojunction (PPHJ) OPD arrays and a customized, rapidly accessible imaging system, the dynamic organic photonics imaging system (DOIS). The resulting PPHJ OPD exhibited a high responsivity (0.6 A W −1 at 868 nm), low dark current (1.5 × 10 −8 A cm −2 at −1 V) and fast response time (480 ns), benefiting from optimal vertical phase separation and donor‐acceptor interface morphology. Moreover, flexible photodetector exhibits superior mechanical stability, photostability and storage stability. Crucially, a pixel‐shifting strategy was incorporated into conventional convolutional neural network (CNN) based machine learning algorithms to capture dynamic images and enhance resolution by leveraging sub‐pixel information sampling. This work demonstrates a significant potential for the extensive application of organic photovoltaic materials in image sensing and flexible electronics.