abcd : Anybody Can Draw

From spade's project page :

We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the network, which is then processed through stacks of convolution, normalization, and nonlinearity layers. We show that this is suboptimal because the normalization layers tend to wash away semantic information. To address the issue, we propose using the input layout for modulating the activations in normalization layers through a spatially-adaptive, learned transformation. Experiments on several challenging datasets demonstrate the advantage of the proposed method compared to existing approaches, regarding both visual fidelity and alignment with input layouts. Finally, our model allows users to easily control the style and content of synthesis results as well as create multi-modal results.
Read more
Collapse
4.0
68 total
5
4
3
2
1
Loading...

What's New

- Release stable version
Read more
Collapse

Additional Information

Updated
June 30, 2019
Size
5.5M
Installs
1,000+
Current Version
1.0.0
Requires Android
4.1 and up
Content Rating
Everyone
Permissions
Offered By
The Apache 64
©2019 GoogleSite Terms of ServicePrivacyDevelopersArtistsAbout Google|Location: United StatesLanguage: English (United States)
By purchasing this item, you are transacting with Google Payments and agreeing to the Google Payments Terms of Service and Privacy Notice.