Learning Controllable ISP for Image Enhancement

Abstract

We present a plug-and-play Image Signal Processor (ISP) for image enhancement to better produce diverse image styles than the previous works. Our proposed method, ContRollable Image Signal Processor (CRISP), explicitly controls the parameters of the ISP that determine output image styles. ISP parameters for high-quality (HQ) image styles are encoded into low-dimensional latent codes, allowing fast and easy style adjustments. We empirically show that CRISP covers a wide range of image styles with high efficiency. On the MIT-Adobe FiveK dataset, CRISP can very closely estimate the reference styles produced by human experts and achieves better MOS with diverse image styles. Compared with the state-of-the-art method, our ISP comprises only 19 parameters, allowing CRISP to have $2\times $ smaller parameters and $100\times $ reduced FLOPs for an image output. CRISP outperforms previous works in PSNR and FLOPs with several scenarios for style adjustments.