Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Several results of our proposed method on various tasks.

Here we show object transformation ((a), (b)) and image style transfer((c)-(f)). The three images from left to right are the source image (which provides the main content), the target image (which provides style and high-level semantic information), and the translated image.

More »

Fig 1 Expand

Fig 2.

CRPGAN network architecture.

In (a) and (b), our model consists of two symmetric pyramids of GANs that gradually refine the generated images from global structure to local details. We start training at ‘scale 0’ by using the lowest resolution image and the smallest generator. With the scale increasing, the size of the generator are gradually increased and the resolution of the image are also changed from low to high. (c) is our Cross-CBAM attention mechanism to extract the image global information and local information.

More »

Fig 2 Expand

Fig 3.

Structure comparison of the different order of channel and spatial attention.

(a) is CBAM attention mechanism including a channel attention and spatial attention mechanism. (b) is the mechanism of two channel followed by two spatial attentions. (c) is the mechanism of two spatial attentions followed by two channel attentions. (d) is our CRCBAM attention mechanism.

More »

Fig 3 Expand

Fig 4.

Channel attention and spatial attention mechanism of CBAM.

More »

Fig 4 Expand

Fig 5.

The visualization results of the different order of channel and spatial attention.

More »

Fig 5 Expand

Table 1.

Quantitative comparison between different order of channel and spatial attention η of CRPGAN in terms of SIFID.

The best scores are in bold.

More »

Table 1 Expand

Fig 6.

Translation results of CRPGAN with various baselines on Summer↔Winter.

Among them, SinGAN is trained using one target domain image, TuiGAN and CRPGAN in this paper are trained using two unpaired images, others are trained using the complete dataset.

More »

Fig 6 Expand

Fig 7.

Translation results of CRPGAN with various baselines on Horse↔Zebra.

More »

Fig 7 Expand

Fig 8.

Translation results of CRPGAN with various baselines on Photo→Van Gogh.

More »

Fig 8 Expand

Table 2.

Average SIFID and training time of various baselines versus our method on general UI2I tasks.

More »

Table 2 Expand

Fig 9.

Results of painting-to-image translation.

We amplify the green box in the translated image at the second row to show more detail.

More »

Fig 9 Expand

Fig 10.

Visual results of scale factor η.

More »

Fig 10 Expand

Table 3.

Quantitative comparison between different scale factor η of CRPGAN in terms of SIFID.

The best scores are in bold.

More »

Table 3 Expand

Fig 11.

Visual results of parametric study.

More »

Fig 11 Expand

Table 4.

Quantitative comparison between different scale factor η of CRPGAN in terms of SIFID.

The best scores are in bold.

More »

Table 4 Expand

Fig 12.

Visual results of ablation study.

More »

Fig 12 Expand

Table 5.

Quantitative comparisons results for CRPGAN ablations study in terms of SIFID.

The best scores are in bold.

More »

Table 5 Expand

Fig 13.

Our model can accurately transfer animal hair color and opera face style features.

More »

Fig 13 Expand