Tsai Fu-Jen, Peng Yan-Tsung, Tsai Chung-Chi, Lin Yen-Yu, Lin Chia-Wen
IEEE Trans Image Process. 2022;31:6789-6799. doi: 10.1109/TIP.2022.3216216. Epub 2022 Oct 28.
Image motion blur results from a combination of object motions and camera shakes, and such blurring effect is generally directional and non-uniform. Previous research attempted to solve non-uniform blurs using self-recurrent multi-scale, multi-patch, or multi-temporal architectures with self-attention to obtain decent results. However, using self-recurrent frameworks typically leads to a longer inference time, while inter-pixel or inter-channel self-attention may cause excessive memory usage. This paper proposes a Blur-aware Attention Network (BANet), that accomplishes accurate and efficient deblurring via a single forward pass. Our BANet utilizes region-based self-attention with multi-kernel strip pooling to disentangle blur patterns of different magnitudes and orientations and cascaded parallel dilated convolution to aggregate multi-scale content features. Extensive experimental results on the GoPro and RealBlur benchmarks demonstrate that the proposed BANet performs favorably against the state-of-the-arts in blurred image restoration and can provide deblurred results in real-time.
图像运动模糊是由物体运动和相机抖动共同造成的，这种模糊效果通常具有方向性且不均匀。先前的研究尝试使用具有自注意力机制的自循环多尺度、多补丁或多时间架构来解决非均匀模糊问题，以获得不错的效果。然而，使用自循环框架通常会导致推理时间变长，而像素间或通道间的自注意力机制可能会导致内存使用过多。本文提出了一种模糊感知注意力网络（BANet），它能够通过单次前向传播实现准确且高效的去模糊。我们的BANet利用基于区域的自注意力机制和多内核带状池化来解析不同大小和方向的模糊模式，并使用级联并行扩张卷积来聚合多尺度内容特征。在GoPro和RealBlur基准测试上的大量实验结果表明，所提出的BANet在模糊图像恢复方面的表现优于现有技术，并且能够实时提供去模糊结果。
