Year: 2023
Type: article
Abstract: Convolutional neural network based methods have been proposed to address blind deblurring. Aiming at the difficulty of reconstructing high-frequency features of images with existing network models, this paper proposes a two-stage convolution-based encoder-decoder for fusing high-frequency a prior. In the first stage, both blurred and high-frequency images are input, and the image features extracted by the network and the high-frequency features are fused. In the second stage, the fused features are further refined and recovered as potentially clear images, and the reconstruction ability of the model for high-frequency features is enhanced. In addition, this paper proposes a deep feature reorganization module that integrates multi-layer semantic information in the encoder-decoder and targets the encoder semantics to further enhance the feature characterization capability of the model. Comprehensive experimental results show that our method achieves 0.9085 structural similarity index (SSIM) and 30.66db peak signal-to-noise ratio (PSNR) on the GoPro dataset. Meanwhile, our method achieves 0.8514 SSIM and 27.39db PSNR on the Lai dataset.
Authors: Meihua Wang, Jiajie Xu, Fanhui Ke, Lei Liao
Institution: South China Agricultural University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $2,890
Awards: G2503486912, G5725060277
OpenAlex ID: W4389449449