Pyramid Architecture Search for Real-Time Image Deblurring

Xiaobin Hu, Wenqi Ren, Kaicheng Yu, Kaihao Zhang, Xiaochun Cao, Wei Liu, Bjoern Menze; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 4298-4307

Abstract


Multi-scale and multi-patch deep models have been shown effective in removing blurs of dynamic scenes. However, these methods still have one major obstacle: manually designing a lightweight and high-efficiency network is challenging and time-consuming. To tackle this problem, 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 the cell searching. Specifically, we introduce a hierarchical search strategy tailored for 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 issue. Furthermore, we use a path-level binarization mechanism for multi-scale cell searching to save memory consumption. Our model 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 dataset.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Hu_2021_ICCV, author = {Hu, Xiaobin and Ren, Wenqi and Yu, Kaicheng and Zhang, Kaihao and Cao, Xiaochun and Liu, Wei and Menze, Bjoern}, title = {Pyramid Architecture Search for Real-Time Image Deblurring}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {4298-4307} }