BANet: A Blur-Aware Attention Network for Dynamic Scene Deblurring

• Published in: IEEE transactions on image processing Vol. 31; pp. 6789 - 6799
• Main Authors: Tsai, Fu-Jen, Peng, Yan-Tsung, Tsai, Chung-Chi, Lin, Yen-Yu, Lin, Chia-Wen
• Format: Journal Article
• Language: English
• Published: New York IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: blur-aware attention module; Blurring; Convolution; Correlation; Feature extraction; Image deblurring; Image restoration; Kernel; Object motion; Real-time systems; region-wise pooling attention; Tensors
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2022.3216216

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.