Online Video Deblurring via Dynamic Temporal Blending Network
원문 초록
State-of-the-art video deblurring methods are capable of removing non-uniform blur caused by unwanted camera shake and/or object motion in dynamic scenes. However, most existing methods are based on batch processing and thus need access to all recorded frames, rendering them computationally demanding and time consuming and thus limiting their practical use. In contrast, we propose an online (sequential) video deblurring method based on a spatio-temporal recurrent network that allows for real-time performance. In particular, we introduce a novel architecture which extends the receptive field while keeping the overall size of the network small to enable fast execution. In doing so, our network is able to remove even large blur caused by strong camera shake and/or fast moving objects. Furthermore, we propose a novel network layer that enforces temporal consistency between consecutive frames by dynamic temporal blending which compares and adaptively (at test time) shares features obtained at different time steps. We show the superiority of the proposed method in an extensive experimental evaluation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Quantile-Based Randomized Kaczmarz for Corrupted Tensor Linear Systems
Video Deblurring by Sharpness Prior Detection and Edge Information
Adaptive High-Pass Kernel Prediction for Efficient Video Deblurring
Learning Truncated Causal History Model for Video Restoration
CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring
Rethinking Video Deblurring with Wavelet-Aware Dynamic Transformer and Diffusion Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.