The high-density, vertically aligned retinal neuron array provides effective vision, a feature we aim to replicate with electronic devices. However, the conventional complementary metal-oxide-semiconductor (CMOS) image sensor, based on separate designs for sensing, memory, and processing units, limits its integration density. Moreover, redundant signal communication significantly increases energy consumption. Current neuromorphic devices integrating sensing and signal processing show promise in various computer vision applications, but there is still a need for frame-based imaging with good compatibility. In this study, we developed a dual-mode image sensor based on a high-density all-inorganic perovskite nanowire array. The device can switch between frame-based standard imaging mode and neuromorphic imaging mode by applying different biases. This unique bias-dependent photo response is based on a well-designed energy band diagram. The biomimetic alignment of nanowires ensures the potential for high-resolution imaging. To further demonstrate the imaging ability, we conducted pattern reconstruction in both modes with a 10 × 10 crossbar device. This study introduces a novel image sensor with high compatibility and efficiency, suitable for various applications including computer vision, surveillance, and robotics.