AMSFF-Net: Attention-Based Multi-Stream Feature Fusion Network for Single Image Dehazing |
| |
Affiliation: | Institute of Computer Science, Shah Abdul Latif University Khairpur, Pakistan |
| |
Abstract: | In this paper, an end-to-end convolutional neural network is proposed to recover haze-free image named as Attention-Based Multi-Stream Feature Fusion Network (AMSFF-Net). The encoder-decoder network structure is used to construct the network. An encoder generates features at three resolution levels. The multi-stream features are extracted using residual dense blocks and fused by feature fusion blocks. AMSFF-Net has ability to pay more attention to informative features at different resolution levels using pixel attention mechanism. A sharp image can be recovered by the good kernel estimation. Further, AMSFF-Net has ability to capture semantic and sharp textural details from the extracted features and retain high-quality image from coarse-to-fine using mixed-convolution attention mechanism at decoder. The skip connections decrease the loss of image details from the larger receptive fields. Moreover, deep semantic loss function emphasizes more semantic information in deep features. Experimental findings prove that the proposed method outperforms in synthetic and real-world images. |
| |
Keywords: | Image dehazing Channel attention Pixel attention Mixed convolution attention Residual dense block Feature fusion |
本文献已被 ScienceDirect 等数据库收录! |