- Session 5: Computer Vision -- Day 3 (Nov.19), poster session: 11:30-14:00, talks: 14:10-15:25 (5th floor Hall 1)
- Poster number: Tue24
- Download paper
Cui Jinkai (Chongqing University); Li Weihong (Chongqing University); Wei Guo (Chongqing university); Gong Weiguo (Chongqing University)
In this paper, we propose an end-to-end multi-width activation and multiple receptive field networks for the large-scale and complicated dynamic scene deblurring. Firstly, we design a multi-width activation feature extraction module, in which a multi-width activation residual block is proposed for making the activation function learn more the nonlinear information and extracting wider nonlinear features. Secondly, we design a multiple receptive field (RF) feature extraction module, in which a multiple RF residual block is proposed for enlarging the RF efficiently and capturing more nonlinear information from distant locations. And then, we design the multi-scale feature fusion module, where a learning fusion structure is designed to adaptively fuse the multi-scale features and complicated blur information from the different modules. Finally, we use a multi-component loss function to jointly optimize our networks. Extensive experimental results demonstrate that the proposed method outperforms the recent state-of-the-art deblurring methods, both quantitatively and qualitatively.