Enhancing Diversity of Defocus Blur Detectors via Cross-Ensemble Network

CVPR 2019 Wenda Zhao Bowen Zheng Qiuhua Lin Huchuan Lu

Defocus blur detection (DBD) is a fundamental yet challenging topic, since the homogeneous region is obscure and the transition from the focused area to the unfocused region is gradual. Recent DBD methods make progress through exploring deeper or wider networks with the expense of high memory and computation... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK LEADERBOARD
Defocus Estimation CUHK - Blur Detection Dataset CENet MAE 0.059 # 1
F-measure 0.906 # 2