Towards Synthesizing Realistic Data for Efficient On-Device Image Deblurring

Existing works on image deblurring operate either with an assumption of white Gaussian noise or ignore the noise term completely in formulating the blur generation process. However, real world images may additionally be corrupted with noise, compression and scaling artifacts, detail loss, etc. The state of the art image deblurring methods do not work well with real images due to this issue. In this work, we propose a blur generation formula that considers composite nature of real world artifacts, enabling deep learning methods to learn an end-to-end mapping between real world blurred and realistic sharp images. We propose an extremely light-weight multiscale-multiresidue architecture, designed for efficient execution on embedded devices (90ms/MP on smartphone). We show the efficacy of our method by comprehensive comparative study against existing methods, on real world blur images as well as popular public deblurring data. Quantitative comparison of our work on public benchmark datasets shows significant improvement (+2.19 dB PSNR) over the state of the art while being almost 100 times faster.