Depth and DOF Cues Make A Better Defocus Blur Detector
This improves image processing for applications like photography and computer vision, but is incremental as it builds on existing methods with new cues.
The paper tackles defocus blur detection by incorporating depth and depth-of-field cues to better distinguish in-focus from out-of-focus regions, outperforming state-of-the-art methods on public benchmarks and a new dataset.
Defocus blur detection (DBD) separates in-focus and out-of-focus regions in an image. Previous approaches mistakenly mistook homogeneous areas in focus for defocus blur regions, likely due to not considering the internal factors that cause defocus blur. Inspired by the law of depth, depth of field (DOF), and defocus, we propose an approach called D-DFFNet, which incorporates depth and DOF cues in an implicit manner. This allows the model to understand the defocus phenomenon in a more natural way. Our method proposes a depth feature distillation strategy to obtain depth knowledge from a pre-trained monocular depth estimation model and uses a DOF-edge loss to understand the relationship between DOF and depth. Our approach outperforms state-of-the-art methods on public benchmarks and a newly collected large benchmark dataset, EBD. Source codes and EBD dataset are available at: https:github.com/yuxinjin-whu/D-DFFNet.