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

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

In this story, Deep Defocus Map Estimation using Domain Adaptation, DMENet, by POSTECH, Sungkyunkwan University, and DGIST, are reviewed. In this paper:

This is a paper in 2019 CVPR with so far 8 citations. (Sik-Ho Tsang @ Medium)


1. The SYNDOF Dataset

1.1. Data Collection

Collection summary of our SYNDOF dataset.

1.2. Thin Lens Model

The thin-lens model

1.3. Defocused Image Generation

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

DMENet: Network Architecture

2.1. Overview

2.2. Training

3. Blur Estimation (B)

Blur Estimation Network (B)

4. Domain Adaptation (D)

The Domain Adaptation Network (D)

4.1. Discriminator Loss

4.2. Adversarial Loss

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

7.1. Evaluation on Subnetworks

Outputs generated with incremental additions of subnetworks in our network

7.2. Evaluation on CUHK and RTF Datasets

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

7.3. Applications

Defocus blur magnification
Depth from our defocus map estimated by DMENet

Though domain adaptation is used, some blur detection results are still inaccurate, which as shown in another later blur detection paper in which the model is named as DeFusionNet. Hope I can write the story about it later as well.


[2019 CVPR] [DMENet]
Deep Defocus Map Estimation using Domain Adaptation

Blur Detection / Defocus Map Estimation

2017 [Park CVPR’17 / DHCF / DHDE] 2018 [Purohit ICIP’18] [BDNet] [DBM] [BTBNet] 2019 [Khajuria ICIIP’19] [Zeng TIP’19] [PM-Net] [CENet] [DMENet] 2020 [BTBCRL (BTBNet + CRLNet)]

Generative Adversarial Network (GAN)

Image Synthesis [GAN] [CGAN] [LAPGAN] [DCGAN] [Pix2Pix]
Super Resolution [SRGAN & SRResNet] [EnhanceNet] [ESRGAN]
Blur Detection [DMENet]
Video Coding

My Other Previous Paper Readings

PhD, Researcher. I share what I've learnt and done. :) My LinkedIn:, My Paper Reading List:

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