Corpus ID: 227336064

Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data

@article{Abuolaim2020LearningTR,
  title={Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data},
  author={Abdullah Abuolaim and M. Delbracio and D. Kelly and M. S. Brown and P. Milanfar},
  journal={ArXiv},
  year={2020},
  volume={abs/2012.03255}
}
Recent work has shown impressive results on data-driven defocus deblurring using the two-image views available on modern dual-pixel (DP) sensors. One significant challenge in this line of research is access to DP data. Despite many cameras having DP sensors, only a limited number provide access to the low-level DP sensor images. In addition, capturing training data for defocus deblurring involves a time-consuming and tedious setup requiring the camera's aperture to be adjusted. Some cameras… Expand
1 Citations

Figures and Tables from this paper

BaMBNet: A Blur-aware Multi-branch Network for Defocus Deblurring

References

SHOWING 1-10 OF 46 REFERENCES
Focus on Defocus: Bridging the Synthetic to Real Domain Gap for Depth Estimation
Modeling Defocus-Disparity in Dual-Pixel Sensors
Deep Defocus Map Estimation Using Domain Adaptation
Non-Parametric Blur Map Regression for Depth of Field Extension
Learning Single Camera Depth Estimation Using Dual-Pixels
Du2Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels
Deep Depth From Focus
Defocus Blur Detection via Multi-stream Bottom-Top-Bottom Fully Convolutional Network
Reflection Removal Using a Dual-Pixel Sensor
Learning Monocular Depth by Distilling Cross-domain Stereo Networks
...
1
2
3
4
5
...