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.

Interior design images generated by different models.

More »

Fig 1 Expand

Fig 2.

Illustration of the proposed DiffDesign.

More »

Fig 2 Expand

Fig 3.

Examples of DesignHelper dataset for public spaces.

More »

Fig 3 Expand

Fig 4.

Examples of DesignHelper dataset for home and leisure spaces.

More »

Fig 4 Expand

Fig 5.

Interior design images generated by our diffusion model for different decoration styles and space functions.

More »

Fig 5 Expand

Fig 6.

Interior design images generated by different diffusion models for different space functions.

More »

Fig 6 Expand

Table 1.

Zero-shot image-text retrieval results on Flickr and MSCOCO datasets.

The best results are marked in bold.

More »

Table 1 Expand

Table 2.

Zero-shot image-text retrieval results on DesignHelper datasets.

The best results are marked in bold.

More »

Table 2 Expand

Table 3.

Comparison of different models based on CLIP Sim and IS and FID across English dataset. The best results are marked in bold.

More »

Table 3 Expand

Fig 7.

Computational efficiency evaluation.

More »

Fig 7 Expand

Fig 8.

Average scores of human preference for six interior design solutions generation models.

More »

Fig 8 Expand

Fig 9.

Renderings of different models generated based on the same prompt.

More »

Fig 9 Expand

Fig 10.

Ablation study of the three modules of the proposed method, i.e., Mclip, Mga, and Mds.

More »

Fig 10 Expand

Table 4.

A brief critical analysis of DiffDesign.

More »

Table 4 Expand