Skip to main content
placeholder image

DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Discriminative Multi-Scale Deep Features

Journal Article


Abstract


  • Albeit great success has been achieved in image defocus blur detection, there are still several unsolved challenges, e.g., interference of background clutter, scale sensitivity and missing boundary details of blur regions. To deal with these issues, we propose a deep neural network which recurrently fuses and refines multi-scale deep features (DeFusionNet) for defocus blur detection. We first fuse the features from different layers of FCN as shallow features and semantic features, respectively. Then, the fused shallow features are propagated to deep layers for refining the details of detected defocus blur regions, and the fused semantic features are propagated to shallow layers to assist in better locating blur regions. The fusion and refinement are carried out recurrently. In order to narrow the gap between low-level and high-level features, we embed a feature adaptation module before feature propagating to exploit the complementary information as well as reduce the contradictory response of different feature layers. Since different feature channels are with different extents of discrimination for detecting blur regions, we design a channel attention module to select discriminative features for feature refinement. Finally, the output of each layer at last recurrent step are fused to obtain the final result. We collect a new dataset consists of various challenging images and their pixel-wise annotations for promoting further study. Extensive experiments on two commonly used datasets and our newly collected one are conducted to demonstrate both the efficacy and efficiency of DeFusionNet.

Publication Date


  • 2022

Citation


  • Tang, C., Liu, X., Zheng, X., Li, W., Xiong, J., Wang, L., . . . Longo, A. (2022). DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Discriminative Multi-Scale Deep Features. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(2). doi:10.1109/TPAMI.2020.3014629

Scopus Eid


  • 2-s2.0-85103762980

Volume


  • 44

Issue


  • 2

Abstract


  • Albeit great success has been achieved in image defocus blur detection, there are still several unsolved challenges, e.g., interference of background clutter, scale sensitivity and missing boundary details of blur regions. To deal with these issues, we propose a deep neural network which recurrently fuses and refines multi-scale deep features (DeFusionNet) for defocus blur detection. We first fuse the features from different layers of FCN as shallow features and semantic features, respectively. Then, the fused shallow features are propagated to deep layers for refining the details of detected defocus blur regions, and the fused semantic features are propagated to shallow layers to assist in better locating blur regions. The fusion and refinement are carried out recurrently. In order to narrow the gap between low-level and high-level features, we embed a feature adaptation module before feature propagating to exploit the complementary information as well as reduce the contradictory response of different feature layers. Since different feature channels are with different extents of discrimination for detecting blur regions, we design a channel attention module to select discriminative features for feature refinement. Finally, the output of each layer at last recurrent step are fused to obtain the final result. We collect a new dataset consists of various challenging images and their pixel-wise annotations for promoting further study. Extensive experiments on two commonly used datasets and our newly collected one are conducted to demonstrate both the efficacy and efficiency of DeFusionNet.

Publication Date


  • 2022

Citation


  • Tang, C., Liu, X., Zheng, X., Li, W., Xiong, J., Wang, L., . . . Longo, A. (2022). DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Discriminative Multi-Scale Deep Features. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(2). doi:10.1109/TPAMI.2020.3014629

Scopus Eid


  • 2-s2.0-85103762980

Volume


  • 44

Issue


  • 2