A low-complexity method for efficient depth-guided image deblurring

TL;DR

This paper presents a low-complexity neural network for depth-guided image deblurring that leverages wavelet transforms and depth information, achieving competitive quality with significantly reduced computational complexity.

Contribution

The paper introduces a novel low-complexity neural network architecture utilizing wavelet transforms and depth guidance for efficient image deblurring.

Findings

Achieves comparable image quality to state-of-the-art models.

Reduces computational complexity by up to two orders of magnitude.

Demonstrates effectiveness of wavelet-based structural separation.

Abstract

Image deblurring is a challenging problem in imaging due to its highly ill-posed nature. Deep learning models have shown great success in tackling this problem but the quest for the best image quality has brought their computational complexity up, making them impractical on anything but powerful servers. Meanwhile, recent works have shown that mobile Lidars can provide complementary information in the form of depth maps that enhance deblurring quality. In this paper, we introduce a novel low-complexity neural network for depth-guided image deblurring. We show that the use of the wavelet transform to separate structural details and reduce spatial redundancy as well as efficient feature conditioning on the depth information are essential ingredients in developing a low-complexity model. Experimental results show competitive image quality against recent state-of-the-art models while reducing complexity by up to two orders of magnitude.