构建了超大规模真实场景模糊图像数据集，用于提升手机视频去模糊模型的泛化能力。
Deblurring in the Wild: A Real-World Image Deblurring Dataset from Smartphone High-Speed Videos
- 用手机慢动作视频合成模糊图像，以中心帧为清晰参考
- 含42,000对高清模糊-清晰图像，规模是现有数据集的10倍
- 涵盖室内外多种运动场景，适合训练鲁棒的去模糊模型
我们构建了迄今为止最大的真实世界图像去模糊数据集，基于智能手机慢动作视频。利用一秒钟内拍摄的240帧画面，通过平均生成模糊图像，以时间中心帧作为清晰参考。数据集包含超过42,000对高分辨率模糊-清晰图像，规模约为常用数据集的10倍，涵盖8倍以上的不同场景，包括室内外环境及多样的物体与相机运动。我们在该数据集上对多个前沿去模糊模型进行基准测试，发现性能显著下降，凸显其复杂性与多样性。该数据集为推动鲁棒且通用的去模糊模型发展提供了极具挑战性的新基准。
原文摘要 · Abstract (English)
We introduce the largest real-world image deblurring dataset constructed from smartphone slow-motion videos. Using 240 frames captured over one second, we simulate realistic long-exposure blur by averaging frames to produce blurry images, while using the temporally centered frame as the sharp reference. Our dataset contains over 42,000 high-resolution blur-sharp image pairs, making it approximately 10 times larger than widely used datasets, with 8 times the amount of different scenes, including indoor and outdoor environments, with varying object and camera motions. We benchmark multiple state-of-the-art (SOTA) deblurring models on our dataset and observe significant performance degradation, highlighting the complexity and diversity of our benchmark. Our dataset serves as a challenging new benchmark to facilitate robust and generalizable deblurring models.
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。