Completed
Problem Description Using deep learning data driven approach to achieve low light imaging
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Learning to See in the Dark - Extreme Low Light Imaging Techniques
Automatically move to the next video in the Classroom when playback concludes
- 1 Problem: Extreme Low Light Imaging
- 2 Related work
- 3 ISO (International Standards Organization)
- 4 Other Solutions Can we change the camera configuration?
- 5 Problem Description Using deep learning data driven approach to achieve low light imaging
- 6 Contributions
- 7 See-in-the-Dark Dataset
- 8 Camera Setup - Output
- 9 Amplification Factor (y)
- 10 Bayer Array
- 11 X-Trans vs. Bayer
- 12 Network Architecture - Training
- 13 ConvNet Block - UNet
- 14 Experimental Evaluation
- 15 Experiment 1a - Perceptual
- 16 Baseline Methods - Denoising
- 17 Experiment 1b: Qualitative - Traditional
- 18 Experiment 1b : Qualitative - BM3D
- 19 Experiment 2: Qualitative - Smartphones
- 20 Evaluation Metrics
- 21 Quantitative Results
- 22 Conclusion
- 23 Ending Remarks
