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.
翻译:目前,基于变压器的算法正在图像除尘器领域产生飞溅。 它们的实现取决于有CNN的自省机制, 以CNN的干线为模型, 来模拟不同象征之间的长期依赖关系。 不幸的是, 这种耳膜燃烧的管道引入了高计算复杂性, 使得很难实时运行单一GPU的超高定义图像。 为了取舍准确性和效率, 输入的退化图像是在三维( $C, $W$和$H$)的信号上进行周期性计算, 而没有自省机制。 我们把这个深层次的网络称为多尺度的 Cubic- Mixer, 在快速的 Fourier 转换以估计 Fourier 系数并因此获得一个淡化的图像后, 以真实和想象的部件来运行。 此外, 我们把多尺度的立方位混合器与一个精度战略结合起来, 以低得多的计算成本来产生高质量结果。 实验结果显示, 拟议的算法在几个基准基准上, 和新的超高速度和超高清晰度定义数据上, 都符合国家水平的脱浮标法方法。