File Download
Links for fulltext
(May Require Subscription)
- Scopus: eid_2-s2.0-85088122806
- WOS: WOS:000534424300052
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Learning to predict layout-to-image conditional convolutions for semantic image synthesis
Title | Learning to predict layout-to-image conditional convolutions for semantic image synthesis |
---|---|
Authors | |
Issue Date | 2019 |
Citation | Advances in Neural Information Processing Systems, 2019, v. 32 How to Cite? |
Abstract | Semantic image synthesis aims at generating photorealistic images from semantic layouts. Previous approaches with conditional generative adversarial networks (GAN) show state-of-the-art performance on this task, which either feed the semantic label maps as inputs to the generator, or use them to modulate the activations in normalization layers via affine transformations. We argue that convolutional kernels in the generator should be aware of the distinct semantic labels at different locations when generating images. In order to better exploit the semantic layout for the image generator, we propose to predict convolutional kernels conditioned on the semantic label map to generate the intermediate feature maps from the noise maps and eventually generate the images. Moreover, we propose a feature pyramid semantics-embedding discriminator, which is more effective in enhancing fine details and semantic alignments between the generated images and the input semantic layouts than previous multi-scale discriminators. We achieve state-of-the-art results on both quantitative metrics and subjective evaluation on various semantic segmentation datasets, demonstrating the effectiveness of our approach. |
Persistent Identifier | http://hdl.handle.net/10722/316550 |
ISSN | 2020 SCImago Journal Rankings: 1.399 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, Xihui | - |
dc.contributor.author | Shao, Jing | - |
dc.contributor.author | Yin, Guojun | - |
dc.contributor.author | Wang, Xiaogang | - |
dc.contributor.author | Li, Hongsheng | - |
dc.date.accessioned | 2022-09-14T11:40:44Z | - |
dc.date.available | 2022-09-14T11:40:44Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | Advances in Neural Information Processing Systems, 2019, v. 32 | - |
dc.identifier.issn | 1049-5258 | - |
dc.identifier.uri | http://hdl.handle.net/10722/316550 | - |
dc.description.abstract | Semantic image synthesis aims at generating photorealistic images from semantic layouts. Previous approaches with conditional generative adversarial networks (GAN) show state-of-the-art performance on this task, which either feed the semantic label maps as inputs to the generator, or use them to modulate the activations in normalization layers via affine transformations. We argue that convolutional kernels in the generator should be aware of the distinct semantic labels at different locations when generating images. In order to better exploit the semantic layout for the image generator, we propose to predict convolutional kernels conditioned on the semantic label map to generate the intermediate feature maps from the noise maps and eventually generate the images. Moreover, we propose a feature pyramid semantics-embedding discriminator, which is more effective in enhancing fine details and semantic alignments between the generated images and the input semantic layouts than previous multi-scale discriminators. We achieve state-of-the-art results on both quantitative metrics and subjective evaluation on various semantic segmentation datasets, demonstrating the effectiveness of our approach. | - |
dc.language | eng | - |
dc.relation.ispartof | Advances in Neural Information Processing Systems | - |
dc.title | Learning to predict layout-to-image conditional convolutions for semantic image synthesis | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_OA_fulltext | - |
dc.identifier.scopus | eid_2-s2.0-85088122806 | - |
dc.identifier.volume | 32 | - |
dc.identifier.isi | WOS:000534424300052 | - |