DeepAI
Log In Sign Up

UHD Image Deblurring via Multi-scale Cubic-Mixer

06/08/2022
by   Zhuoran Zheng, et al.
0

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.

READ FULL TEXT

page 3

page 4

page 6

page 7

page 8

12/02/2019

Multi-Scale Self-Attention for Text Classification

In this paper, we introduce the prior knowledge, multi-scale structure, ...
11/17/2019

MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning

In sequence to sequence learning, the self-attention mechanism proves to...
07/01/2021

Global Filter Networks for Image Classification

Recent advances in self-attention and pure multi-layer perceptrons (MLP)...
01/19/2021

BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring

Image motion blur usually results from moving objects or camera shakes. ...
07/22/2021

FNetAR: Mixing Tokens with Autoregressive Fourier Transforms

In this note we examine the autoregressive generalization of the FNet al...
03/21/2022

Fourier Disentangled Space-Time Attention for Aerial Video Recognition

We present an algorithm, Fourier Activity Recognition (FAR), for UAV vid...