Review — PM-Net: Accurate and Fast Blur Detection Using a Pyramid M-Shaped Deep Neural Network (Blur Detection)

Using a Pyramid M-Shaped Deep Neural Network, Outperforms Park CVPR’17 & Zeng TIP’19, etc.

Examples of (a) globally blurred image, (b) © partially motion-blurred images, and (d) partially defocused image.

Outline

1. M-Shaped Network

M-Shaped Network

1.1. Overall Network Architecture

Detailed configuration of each stage

1.2. Multi-Input Pyramid

1.3. Multi-Loss Pyramid

1.4. New Skip Connection

2. Pyramid M-Shaped Network (PM-Net)

Upper Part: Pyramid M-Shaped Network (PM-Net), Lower Part: A M-Shaped Network

3. Ablation Study

Effectiveness analysis of multi-input pyramid (first from the left), multi-loss pyramid (second from the left), and multi-model pyramid (right side) using F1-score.
Effectiveness analysis of individual M-shaped network

4. Experimental Results

4.1. Qualitative Results

Defocus Blur Detection Results: (a) Inputs. (b) Results of Su et al. [13]. (c) Results of Shi et al. [14]. (d) Results of Javaran et al. [20]. (e) Results of Golestaneh et al. [36]. (f) Results of Shi et al. [35]. (g) Results of Park et al. [22]. (h) Results of Zeng et al. [25]. (i) Results of PM¹-Net. (j) Results of PM³-Net. (k) Ground truth.
Motion Blur Detection Results: (a) Inputs. (b) Results of Liu et al. [12]. (c) Results of Shi et al. [14]. (d) Results of Su et al. [13]. (e) Results of Javaran et al. [20]. (f) Results of Golestaneh et al. [36]. (g) Results of PM¹-Net. (h) Results of PM³-Net. (i) Ground truth.
(a) Inputs. (b) Results of our method. (c) Ground Truth.
(a) Inputs. (b) Results of our method. (c) Ground Truth.
(a) Inputs. (b) Results of our method. (c) Ground Truth.

4.2. Quantitative Results

Performance comparisons among different blur detection methods on BDD. (Shi’s Dataset)
Comparison of precision-recall curves of the state-of-the-art methods on BDD. (Shi’s Dataset)

5.3. Cross Dataset Results

Performance comparisons for cross-dataset evaluation on the CDD dataset.
(a) Input. (b) Golestaneh et al. [36]. (c) Shi et al. [35]. (d) Zhao et al. [24]. (e) PM1-Net. (f) PM3-Net. (g) Ground Truth.

5.5. Running Time

Runtime comparisons among different methods for a 640×512 defocused image.

PhD, Researcher. I share what I've learnt and done. :) My LinkedIn: https://www.linkedin.com/in/sh-tsang/, My Paper Reading List: https://bit.ly/33TDhxG