Jung, Hyungjoo Kim, Youngjung Jang, Hyunsung Ha, Namkoo Sohn, Kwanghoon 2024-01-19T14:01:12Z 2024-01-19T14:01:12Z 2022-01-10 2021-09 1057-7149 https://pubs.kist.re.kr/handle/201004/116516 Motion blur, which disturbs human and machine perceptions of a scene, has been considered an unnecessary artifact that should be removed. However, the blur can be a useful clue to understanding the dynamic scene, since various sources of motion generate different types of artifacts. Motivated by the relationship between motion and blur, we propose a motion-aware feature learning framework for dynamic scene deblurring through multi-task learning. Our multi-task framework simultaneously estimates a deblurred image and a motion field from a blurred image. We design the encoder-decoder architectures for two tasks, and the encoder part is shared between them. Our motion estimation network could effectively distinguish between different types of blur, which facilitates image deblurring. Understanding implicit motion information through image deblurring could improve the performance of motion estimation. In addition to sharing the network between two tasks, we propose a reblurring loss function to optimize the overall parameters in our multi-task architecture. We provide an intensive analysis of complementary tasks to show the effectiveness of our multi-task framework. Furthermore, the experimental results demonstrate that the proposed method outperforms the state-of-the-art deblurring methods with respect to both qualitative and quantitative evaluations. English IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC KERNEL ESTIMATION DEPTH ESTIMATION NETWORK Multi-Task Learning Framework for Motion Estimation and Dynamic Scene Deblurring Article 10.1109/TIP.2021.3113185 1 IEEE TRANSACTIONS ON IMAGE PROCESSING, v.30, pp.8170 - 8183 IEEE TRANSACTIONS ON IMAGE PROCESSING 30 8170 8183 scie scopus 000701249000007 2-s2.0-85115683147 Computer Science, Artificial Intelligence Engineering, Electrical & Electronic Computer Science Engineering Article KERNEL ESTIMATION DEPTH ESTIMATION NETWORK Kernel Dynamics Task analysis Cameras Motion estimation Image restoration Estimation Motion blur dynamic scene deblurring motion estimation multi-task learning