@techreport{oai:ipsj.ixsq.nii.ac.jp:00209803,
 author = {深津, 佑太 and 青野, 雅樹 and Yuta, Fukatsu and Masaki, Aono},
 issue = {5},
 month = {Feb},
 note = {近年，GAN によるクラスラベルやテキストで条件を与えるタイプの条件付き画像生成の研究が成功を収めている．一方，3D メッシュの条件付き 3D モデルの生成はいまだ発展途上である．本論文では Attentive Normalization に基づく大域情報を用いて 3D メッシュ生成の向上を行う．また，条件情報を付与可能な Conditional Attentive Normalization を提案する．Caltech-UCSD Birds-200-2011 データセットを用いて従来手法とのクラスラベルおよびテキストによる生成の比較実験を行った結果，提案手法は従来手法よりも優れていることが示されたので，これを報告する．, In recent years, research on conditional image generation using GANs of the type where conditions are given by class labels or texts has been successful. On the other hand, the generation of conditional 3D models consisting of 3D meshes is still in its infancy. In this research, we focus on global information based on Attentive Normalization to improve 3D mesh generation. Specifically, we propose Conditional Attentive Normalization, which is an extension of Attentive Normalization and can add conditional information. Comparative experiments conditioned by class labels and texts have been carried out by using Caltech-UCSD Birds-200-201. It turns out that our proposed method outperforms the conventional methods.},
 title = {Attentive Normalizationを拡張した3Dメッシュの自動生成},
 year = {2021}
}