Review — DMENet: Deep Defocus Map Estimation using Domain Adaptation (Blur Detection)

Using Domain Adaptation, Dataset with Synthetic Blurring is used, Outperforms Park CVPR’17

Outline

1. The SYNDOF Dataset

Collection summary of our SYNDOF dataset.
The thin-lens model

2. DMENet: Network Architecture (B+D+C+S)

DMENet: Network Architecture

3. Blur Estimation (B)

Blur Estimation Network (B)

4. Domain Adaptation (D)

The Domain Adaptation Network (D)

5. Content Preservation (C)

The Content Preservation Network (C)

6. Sharpness Calibration (S)

Sharpness Calibration Network (S)

In other words, the blur amounts learned by our blur estimation network B for synthetic defocused images cannot be readily applied to real defocused images, and we need to calibrate the estimated blur amounts for the two domains.

7. Experimental Results

Outputs generated with incremental additions of subnetworks in our network
Accuracy comparison on CUHK dataset
Precision-Recall comparison on CUHK dataset
(a) Input and the defocus maps estimated by (b) Zhou et al. [40], (c) Shi et al. [30], (d) Park et al. [24], (e) Karaali et al. [13], (f) ours, and (g) ground-truth
Left: Input, Middle: defocus map estimated by [38] and Right: DMENet
MSE and MAE on RTF dataset
Defocus blur magnification
Deblurring
Depth from our defocus map estimated by DMENet

--

--

PhD, Researcher. I share what I learn. :) Linktree: https://linktr.ee/shtsang for Twitter, LinkedIn, etc.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store