Blurry images are not only visually unappealing, but they also degrade the performance of computer vision applications dramatically. As a result, motion deblurring for the thermal infrared picture plays a critical role in infrared systems. In recent years, convolutional neural network-based image deblurring methods have yielded promising performance with remarkable results and low computational cost. Inspired by these works, in this paper, we investigate an end-to-end deblurring model for single blurred thermal IR image by adopting the multi-input approach. Our model achieve PSNR and SSIM scores of 31.83 and 0.6435 when evaluating on our blur-sharp thermal infrared image pair dataset. Furthermore, the lightweight nature of our model allows it to operate at 140 FPS when inferring on Tesla V100 GPU.
Paper
Full text
Deep learning-based infrared image deblurring
Semantic Scholar · Computer Science · 2022
Abstract
Blurry images are not only visually unappealing, but they also degrade the performance of computer vision applications dramatically. As a result, motion deblurring for the thermal infrared picture plays a critical role in infrared systems. In recent years, convolutional neural network-based image deblurring methods have yielded promising performance with remarkable results and low computational cost. Inspired by these works, in this paper, we investigate an end-to-end deblurring model for single blurred thermal IR image by adopting the multi-input approach. Our model achieve PSNR and SSIM scores of 31.83 and 0.6435 when evaluating on our blur-sharp thermal infrared image pair dataset. Furthermore, the lightweight nature of our model allows it to operate at 140 FPS when inferring on Tesla V100 GPU.