Limited by hardware conditions and complex degradation processes, aerial images obtained by drone reconnaissance are usually blurry data lacking high-frequency information. To address this problem, many image deblurri...
详细信息
Limited by hardware conditions and complex degradation processes, aerial images obtained by drone reconnaissance are usually blurry data lacking high-frequency information. To address this problem, many image deblurring algorithms have been proposed. Although significant progress has been made, there are still some challenges in aerial image deblurring, such as low-performance deblurring and non real-time processing. In this work, we propose a progressive residual recurrent network (PRRN) for aerial image deblurring and make four contributions to overcoming the above challenges: (1) We design a lightweight encoder-decoder module (LEDM) which includes the progressive residual block and the feature recurrent structure (FRS), and we can control the number of LEDMs to balance the deblurring efficiency and performance. (2) We present the progressive residual block, which adopts simple gate to reduce the system complexity and introduces layer normalization to stabilize the training process. (3) We present the FRS composed of feature map recurrence and latent code recurrence to retain and remove the feature information of previous encoder-decodermodules. (4) We adopt aerial images from DOTA dataset as the initial data and use the motion blur kernel to generate blurry aerial images, aiming at forming a dataset named AID for aerial image deblurring. Extensive experiments on synthetic and our datasets prove the superior performance of PRRN in terms of quantitative and qualitative evaluation. Notably, our proposed network reaches 30.80 dB PSNR on AID dataset and 77.73% mAP on realistic blurry aerial images, which achieves state-of-the-art deblurring performance.
暂无评论