论文标题
超高定义图像通过多尺度立方混合物去蓝色
Ultra-High-Definition Image Deblurring via Multi-scale Cubic-Mixer
论文作者
论文摘要
当前，基于变压器的算法正在在图像脱毛的域中引起飞溅。它们的成就取决于CNN茎的自我发挥机制，以模拟令牌之间的长距离依赖性。不幸的是，这种令人愉悦的管道引入了较高的计算复杂性，因此很难实时在单个GPU上运行超高定义图像。为了权衡准确性和效率，在没有自我注意力的机制的情况下，在三维（$ c $，$ w $和$ h $）信号的三维（$ c $，$ w $和$ h $）信号上循环计算出降级图像。我们将此深层网络称为多尺度立方混合物，在快速傅立叶变换后，该网络在真实和虚构的组件上都作用，以估计傅立叶系数，从而获得脱毛的图像。此外，我们将多尺度的立方混合物与切片策略相结合，以低得多的计算成本产生高质量结果。实验结果表明，所提出的算法对几个基准的最先进的脱蓝色方法和新的超高定义数据集的性能表现出色。
Currently, transformer-based algorithms are making a splash in the domain of image deblurring. Their achievement depends on the self-attention mechanism with CNN stem to model long range dependencies between tokens. Unfortunately, this ear-pleasing pipeline introduces high computational complexity and makes it difficult to run an ultra-high-definition image on a single GPU in real time. To trade-off accuracy and efficiency, the input degraded image is computed cyclically over three dimensional ($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.
