Ultra-High-Definition Image Deblurring via Multi-scale Cubic-Mixer

TL;DR

This paper introduces the Multi-scale Cubic-Mixer, a novel deep learning approach for ultra-high-definition image deblurring that balances accuracy and efficiency by avoiding self-attention mechanisms and leveraging Fourier transforms.

Contribution

The paper proposes a new multi-scale cubic-mixer network that estimates Fourier coefficients for deblurring, enabling real-time processing of ultra-high-definition images with reduced computational cost.

Findings

Outperforms state-of-the-art methods on multiple benchmarks

Achieves high-quality deblurring with lower computational cost

Effective on ultra-high-definition images in real-time

Abstract

Currently, transformer-based algorithms are making a splash in the domain of image deblurring. Their achievement depends on the self-attention mechanism with CNN stem to model long range dependencies between tokens. Unfortunately, this ear-pleasing pipeline introduces high computational complexity and makes it difficult to run an ultra-high-definition image on a single GPU in real time. To trade-off accuracy and efficiency, the input degraded image is computed cyclically over three dimensional ($C$, $W$, and $H$) signals without a self-attention mechanism. We term this deep network as Multi-scale Cubic-Mixer, which is acted on both the real and imaginary components after fast Fourier transform to estimate the Fourier coefficients and thus obtain a deblurred image. Furthermore, we combine the multi-scale cubic-mixer with a slicing strategy to generate high-quality results at a much lower computational cost. Experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art deblurring approaches on the several benchmarks and a new ultra-high-definition dataset in terms of accuracy and speed.