@techreport{oai:ipsj.ixsq.nii.ac.jp:00229206,
 author = {Chattarin, Rodpon and Yoshihiro, Kanamori and Yuki, Endo and Chattarin, Rodpon and Yoshihiro, Kanamori and Yuki, Endo},
 issue = {39},
 month = {Nov},
 note = {We propose 3D-aware semantic image synthesis by explicitly introducing 3D information to semantic image synthesis. Existing methods of semantic image synthesis try to translate a semantic mask to a realistic RGB image directly. However, semantic masks neither convey sufficient information on the 3D scene structure nor interior shapes within the masks, making 3D-aware image synthesis a challenging task. To tackle this problem, we integrate 3D scene knowledge as depth information into image synthesis by introducing a multi-task network which not only generates an RGB image but also a depth representation. We also introduce a wireframe parsing loss to further enforce 3D scene structure in image generation. We demonstrate that our method outperforms baseline methods across several datasets via qualitative and quantitative evaluations., We propose 3D-aware semantic image synthesis by explicitly introducing 3D information to semantic image synthesis. Existing methods of semantic image synthesis try to translate a semantic mask to a realistic RGB image directly. However, semantic masks neither convey sufficient information on the 3D scene structure nor interior shapes within the masks, making 3D-aware image synthesis a challenging task. To tackle this problem, we integrate 3D scene knowledge as depth information into image synthesis by introducing a multi-task network which not only generates an RGB image but also a depth representation. We also introduce a wireframe parsing loss to further enforce 3D scene structure in image generation. We demonstrate that our method outperforms baseline methods across several datasets via qualitative and quantitative evaluations.},
 title = {3D-aware Semantic Image Synthesis},
 year = {2023}
}