期刊
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
卷 -, 期 -, 页码 4278-4287出版社
IEEE
DOI: 10.1109/ICCV48922.2021.00426
关键词
-
资金
- National Key RD Program of China [2020YFB1406704]
- National Natural Science Foundation of China [61802403, 62025604, U1936210, 61971016]
The study introduces a deblurring method called PyNAS that automatically designs hyper-parameters, utilizing gradient-based and hierarchical search strategies to achieve real-time deblurring algorithm and state-of-the-art performance on GoPro and Video Deblurring datasets.
Multi-scale and multi-patch deep models have been shown effective in removing blurs of dynamic scenes. However, these methods still suffer from one major obstacle: manually designing a lightweight and high-efficiency network is challenging and time-consuming. To tackle this obstacle, we propose a novel deblurring method, dubbed PyNAS (pyramid neural architecture search network), towards automatically designing hyper-parameters including the scales, patches, and standard cell operators. The proposed PyNAS adopts gradient-based search strategies and innovatively searches the hierarchy patch and scale scheme not limited to cell searching. Specifically, we introduce a hierarchical search strategy tailored to the multi-scale and multi-patch deblurring task. The strategy follows the principle that the first distinguishes between the top-level (pyramid-scales and pyramid-patches) and bottom-level variables (cell operators) and then searches multi-scale variables using the top-to-bottom principle. During the search stage, PyNAS employs an early stopping strategy to avoid the collapse and computational issues. Furthermore, we use a path-level binarization mechanism for multi-scale cell searching to save the memory consumption. Our primary contribution is a real-time deblurring algorithm (around 58 fps) for 720p images while achieves state-of-the-art deblurring performance on the GoPro and Video Deblurring datasets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据