Deep Dynamic Scene Deblurring from Optical Flow
원문 초록
Deblurring can not only provide visually more pleasant pictures and make photography more convenient, but also can improve the performance of objection detection as well as tracking. However, removing dynamic scene blur from images is a non-trivial task as it is difficult to model the non-uniform blur mathematically. Several methods first use single or multiple images to estimate optical flow (which is treated as an approximation of blur kernels) and then adopt non-blind deblurring algorithms to reconstruct the sharp images. However, these methods cannot be trained in an end-to-end manner and are usually computationally expensive. In this paper, we explore optical flow to remove dynamic scene blur by using the multi-scale spatially variant recurrent neural network (RNN). We utilize FlowNets to estimate optical flow from two consecutive images in different scales. The estimated optical flow provides the RNN weights in different scales so that the weights can better help RNNs to remove blur in the feature spaces. Finally, we develop a convolutional neural network (CNN) to restore the sharp images from the deblurred features. Both quantitative and qualitative evaluations on the benchmark datasets demonstrate that the proposed method performs favorably against state-of-the-art algorithms in terms of accuracy, speed, and model size.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Event-Enhanced Blurry Video Super-Resolution
EV-LayerSegNet: Self-supervised Motion Segmentation using Event Cameras
Generative Latent Kernel Modeling for Blind Motion Deblurring
MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation
EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
WAFT: Warping-Alone Field Transforms for Optical Flow
토론
이 논문과 연결된 포럼 글이 아직 없습니다.