CAIR: Fast and Lightweight Multi-Scale Color Attention Network for Instagram Filter Removal
CAIR: Fast and Lightweight Multi-Scale Color Attention Network for Instagram Filter Removal
复制标题
CAIR：用于 Instagram 滤镜去除的快速、轻量级多尺度颜色注意网络
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Han
中科院分区：
文献类型：
--
作者：
Woon;Wang;Kyung;Young;Han
图像复原是计算机视觉中一个重要而又具有挑战性的课题。将过滤后的图像恢复为原始图像有助于各种计算机视觉任务。我们采用了一个非线性激活函数自由网络（NAFNet）的快速和轻量级的模型，并添加了一个颜色注意模块，提取有用的颜色信息，以提高准确性。我们提出了一个准确，快速，轻量级的网络与多尺度和颜色注意Instagram过滤器删除（CAIR）。实验结果表明，CAIR在快速和轻量级的方面优于现有的Instagram过滤器删除网络，约为11美元。 速度加快一倍， 在IFFI数据集上的PSNR超过3.69 dB时，CAIR可以成功地去除高质量的Instagram滤镜，并在定性结果中恢复颜色信息。源代码和预训练的权重可在url{https：//github.com/HnV-Lab/CAIR}上获得。
Image restoration is an important and challenging task in computer vision. Reverting a filtered image to its original image is helpful in various computer vision tasks. We employ a nonlinear activation function free network (NAFNet) for a fast and lightweight model and add a color attention module that extracts useful color information for better accuracy. We propose an accurate, fast, lightweight network with multi-scale and color attention for Instagram filter removal (CAIR). Experiment results show that the proposed CAIR outperforms existing Instagram filter removal networks in fast and lightweight ways, about 11$ imes$ faster and 2.4$ imes$ lighter while exceeding 3.69 dB PSNR on IFFI dataset. CAIR can successfully remove the Instagram filter with high quality and restore color information in qualitative results. The source code and pretrained weights are available at url{https://github.com/HnV-Lab/CAIR}.