2026-03-15T05:11:58Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00229206 2025-01-19T11:36:07Z 1164:6757:11095:11361

3D-aware Semantic Image Synthesis 3D-aware Semantic Image Synthesis Chattarin, Rodpon Yoshihiro, Kanamori Yuki, Endo Chattarin, Rodpon Yoshihiro, Kanamori Yuki, Endo 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. technical report 情報処理学会 2023-11-09 application/pdf 研究報告デジタルコンテンツクリエーション（DCC） 39 2023-DCC-35 1 6 2188-8868 AA12628338 https://ipsj.ixsq.nii.ac.jp/record/229206/files/IPSJ-DCC23035039.pdf eng