当前位置: X-MOL 学术J. Real-Time Image Proc. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
BAM: a balanced attention mechanism to optimize single image super-resolution
Journal of Real-Time Image Processing ( IF 3 ) Pub Date : 2022-07-26 , DOI: 10.1007/s11554-022-01235-x
Fanyi Wang, Haotian Hu, Cheng Shen, Tianpeng Feng, Yandong Guo

Recovering texture information from the aliasing regions has always been a major challenge for single image super-resolution (SISR) task. These regions are often submerged in noise so that we have to restore texture details while suppressing noise. To address this issue, we propose an efficient Balanced Attention Mechanism (BAM), which consists of Avgpool Channel Attention Module (ACAM) and Maxpool Spatial Attention Module (MSAM) in parallel. ACAM is designed to suppress extreme noise in the large-scale feature maps, while MSAM preserves high-frequency texture details. Thanks to the parallel structure, these two modules not only conduct self-optimization, but also mutual optimization to obtain the balance of noise reduction and high-frequency texture restoration during the back propagation process, and the parallel structure makes the inference faster. To verify the effectiveness and robustness of BAM, we applied it to 10 state-of-the-art SISR networks. The results demonstrate that BAM can efficiently improve the networks' performance, and for those originally with attention mechanism, the substitution with BAM further reduces the amount of parameters and increases the inference speed. Information multi-distillation network (IMDN), a representative lightweight SISR network with attention, when the input image size is 200 × 200, the FPS of proposed IMDN-BAM precedes IMDN {8.1%, 8.7%, 8.8%} under the three SR magnifications of × 2, × 3, × 4, respectively. Densely residual Laplacian network (DRLN), a representative heavyweight SISR network with attention, when the scale is 60 × 60, the proposed DRLN-BAM is {11.0%, 8.8%, 10.1%} faster than DRLN under × 2, × 3, × 4. Moreover, we present a dataset with rich texture aliasing regions in real scenes, named realSR7. Experiments prove that BAM achieves better super-resolution results on the aliasing area.



中文翻译:

BAM:一种优化单幅图像超分辨率的平衡注意力机制

从混叠区域恢复纹理信息一直是单图像超分辨率(SISR)任务的主要挑战。这些区域经常被噪声淹没,因此我们必须在抑制噪声的同时恢复纹理细节。为了解决这个问题,我们提出了一种高效的平衡注意力机制(BAM),它由并行的 Avgpool 通道注意力模块(ACAM)和 Maxpool 空间注意力模块(MSAM)组成。ACAM 旨在抑制大规模特征图中的极端噪声,而 MSAM 保留高频纹理细节。得益于并行结构,这两个模块不仅进行自我优化,而且相互优化,在反向传播过程中获得降噪和高频纹理恢复的平衡,并行结构使推理更快。为了验证 BAM 的有效性和稳健性,我们将其应用于 10 个最先进的 SISR 网络。结果表明,BAM 可以有效地提高网络的性能,对于那些原本具有注意力机制的网络,用 BAM 进行替换进一步减少了参数量并提高了推理速度。Information multi-distillation network (IMDN),一种有代表性的带注意力的轻量级SISR网络,当输入图像大小为200×200时,提出的IMDN-BAM的FPS在三种SR下领先于IMDN {8.1%, 8.7%, 8.8%}放大倍数分别为×2、×3、×4。密集残差拉普拉斯网络(DRLN),一个有代表性的具有注意力的重量级SISR网络,当规模为60×60时,提出的DRLN-BAM为{11.0%, 8.8%, 10。在×2、×3、×4下比DRLN快1%}。此外,我们提出了一个在真实场景中具有丰富纹理混叠区域的数据集,名为realSR7。实验证明,BAM 在混叠区域取得了较好的超分辨率效果。

更新日期:2022-07-27
down
wechat
bug