提出新数据集与模型，提升视频去模糊的精度与适应性。
Video Deblurring by Sharpness Prior Detection and Edge Information
- 通过可调锐化帧频率构建新数据集，增强训练多样性。
- 在多数据集上实现平均3.2%的PSNR提升，优于现有方法。
- 适合自动驾驶、安防等需要高鲁棒性的视频处理场景。
视频去模糊在自动驾驶、人脸识别和安全监控中至关重要。传统方法直接估计运动模糊核，常引入伪影且效果不佳。近期方法利用视频序列中锐化帧的检测来提升去模糊性能，但现有数据集固定锐化帧数量，限制了应用场景并可能造成训练偏差。为此，本文首次提出GoPro Random Sharp（GoProRS）数据集，支持灵活调节序列内锐化帧频率，实现更丰富的训练与测试场景。同时提出SPEINet模型，采用基于注意力的编码器-解码器架构，融合锐化帧特征，并结合轻量级锐化帧检测与边缘提取模块，用于模糊帧重建。大量实验表明，SPEINet在多个数据集上均超越当前最优方法，平均提升3.2% PSNR。结果表明，该模型与数据集为基于锐化帧检测的视频去模糊研究提供了新方向。
原文摘要 · Abstract (English)
Video deblurring is essential task for autonomous driving, facial recognition, and security surveillance. Traditional methods directly estimate motion blur kernels, often introducing artifacts and leading to poor results. Recent approaches utilize the detection of sharp frames within video sequences to enhance deblurring. However, existing datasets rely on fixed number of sharp frames, which may be too restrictive for some applications and may introduce a bias during model training. To address these limitations and enhance domain adaptability, this work first introduces GoPro Random Sharp (GoProRS), a new dataset where the the frequency of sharp frames within the sequence is customizable, allowing more diverse training and testing scenarios. Furthermore, it presents a novel video deblurring model, called SPEINet, that integrates sharp frame features into blurry frame reconstruction through an attention-based encoder-decoder architecture, a lightweight yet robust sharp frame detection and an edge extraction phase. Extensive experimental results demonstrate that SPEINet outperforms state-of-the-art methods across multiple datasets, achieving an average of +3.2% PSNR improvement over recent techniques. Given such promising results, we believe that both the proposed model and dataset pave the way for future advancements in video deblurring based on the detection of sharp frames.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。