DAVID: Dual-Attentional Video Deblurring
원문 초록
Blind video deblurring restores sharp frames from a blurry sequence without any prior. It is a challenging task because the blur due to camera shake, object movement and defocusing is heterogeneous in both temporal and spatial dimensions. Traditional methods train on datasets synthesized with a single level of blur, and thus do not generalize well across levels of blurriness. To address this challenge, we propose a dual attention mechanism to dynamically aggregate temporal cues for deblurring with an end-to-end trainable network structure. Specifically, an internal attention module adaptively selects the optimal temporal scales for restoring the sharp center frame. An external attention module adaptively aggregates and refines multiple sharp frame estimates, from several internal attention modules designed for different blur levels. To train and evaluate on more diverse blur severity levels, we propose a Challenging DVD dataset generated from the raw DVD video set by pooling frames with different temporal windows. Our framework achieves consistently better performance on this more challenging dataset while obtaining strongly competitive results on the original DVD benchmark. Extensive ablative studies and qualitative visualizations further demonstrate the advantage of our method in handling real video blur.
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.