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 achieves 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.
Human head pose estimation is an essential problem in facial analysis in recent years that has a lot of computer vision applications such as gaze estimation, virtual reality, driver assistance. Because of the importance of the head pose estimation problem, it is necessary to design a compact model to resolve this task in order to reduce the computational cost when deploying on facial analysis-based applications such as large camera surveillance systems, AI cameras while maintaining accuracy. In this work, we propose a lightweight model that effectively addresses the head pose estimation problem. Our approach has two main steps. 1) We first train many teacher models on the synthesis dataset -300W-LPA to get the head pose pseudo labels. 2) We design an architecture with the ResNet18 backbone and train our proposed model with the ensemble of these pseudo labels via the knowledge distillation process. To evaluate the effectiveness of our model, we use AFLW-2000 and BIWItwo real-world head pose datasets. Experimental results show that our proposed model significantly improves the accuracy in comparison with the state-of-the-art head pose estimation methods. Furthermore, our model has the real-time speed of ∼300 FPS when inferring on Tesla V100.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.