arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.09059cs.CV
收藏

通过测试时模糊实现域自适应视频去模糊

Domain-adaptive Video Deblurring via Test-time Blurring

National Yang Ming Chiao Tung University(国立阳明交通大学);National Tsing Hua University(国立清华大学);National Chengchi University(国立政治大学);Qualcomm Technologies, Inc.(高通技术公司)

Jin-Ting He, Fu-Jen Tsai, Jia-Hao Wu, Yan-Tsung Peng, Chung-Chi Tsai, Chia-Wen Lin, Yen-Yu Lin

AI总结:

针对训练与测试视频的域差距导致去模糊性能下降的问题,提出基于模糊模型的测试时域自适应方案,通过生成域适配的伪清晰-模糊对微调模型,最高提升7.54dB的去模糊性能。

摘要:

动态场景视频去模糊旨在消除曝光过程中产生的不良模糊伪影。尽管以往的视频去模糊方法已取得出色效果,但由于训练视频与测试视频之间存在域差距,其性能会出现显著下降,针对真实场景下拍摄的视频尤为明显。为解决这一问题,我们提出一种基于模糊模型的域自适应方案,实现去模糊模型在未见过的域上的测试时微调。由于推理阶段没有成对的模糊-清晰图像可用于微调,我们的方案能够生成域自适应的训练对,为目标域校准去模糊模型。首先,我们提出相对清晰度检测模块(Relative Sharpness Detection Module),从模糊输入图像中识别出相对清晰的区域,将其作为伪清晰图像。接着,我们利用模糊模型,基于测试过程中提取的伪清晰图像生成模糊图像。为合成符合目标数据分布的模糊图像,我们提出域自适应模糊条件生成模块(Domain-adaptive Blur Condition Generation Module),为模糊模型创建域特定的模糊条件。最后,利用生成的伪清晰图像与模糊图像对微调去模糊模型,以提升性能。大量实验结果表明,我们的方法能显著提升现有最优视频去模糊方法的性能,在多个真实世界视频去模糊数据集上的性能提升最高可达7.54dB。源代码可在https://github.com/Jin-Ting-He/DADeblur 获取。

英文摘要:

Dynamic scene video deblurring aims to remove undesirable blurry artifacts captured during the exposure process. Although previous video deblurring methods have achieved impressive results, they suffer from significant performance drops due to the domain gap between training and testing videos, especially for those captured in real-world scenarios. To address this issue, we propose a domain adaptation scheme based on a blurring model to achieve test-time fine-tuning for deblurring models in unseen domains. Since blurred and sharp pairs are unavailable for fine-tuning during inference, our scheme can generate domain-adaptive training pairs to calibrate a deblurring model for the target domain. First, a Relative Sharpness Detection Module is proposed to identify relatively sharp regions from the blurry input images and regard them as pseudo-sharp images. Next, we utilize a blurring model to produce blurred images based on the pseudo-sharp images extracted during testing. To synthesize blurred images in compliance with the target data distribution, we propose a Domain-adaptive Blur Condition Generation Module to create domain-specific blur conditions for the blurring model. Finally, the generated pseudo-sharp and blurred pairs are used to fine-tune a deblurring model for better performance. Extensive experimental results demonstrate that our approach can significantly improve state-of-the-art video deblurring methods, providing performance gains of up to 7.54dB on various real-world video deblurring datasets. The source code is available at https://github.com/Jin-Ting-He/DADeblur.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑