You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Frans, Kevin, L. B. Soros, and Olaf Witkowski. 2021. “CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders.” arXiv [cs.CV]. arXiv. http://arxiv.org/abs/2106.14843.
Fernando, Chrisantha, S. M. Ali Eslami, Jean-Baptiste Alayrac, Piotr Mirowski, Dylan Banarse, and Simon Osindero. 2021. “Generative Art Using Neural Visual Grammars and Dual Encoders.” arXiv [cs.AI]. arXiv. http://arxiv.org/abs/2105.00162.
Radford, Alec, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, et al. 2021. “Learning Transferable Visual Models From Natural Language Supervision.” arXiv [cs.CV]. arXiv. http://arxiv.org/abs/2103.00020.
CLIP論文
Li, Tzu-Mao, Michal Lukáč, Michaël Gharbi, and Jonathan Ragan-Kelley. 2020. “Differentiable Vector Graphics Rasterization for Editing and Learning.” ACM Transactions on Graphics, 193, 39 (6): 1–15.
この研究で使われている微分可能なレンダラの提案論文
The text was updated successfully, but these errors were encountered:
CLIPと微分可能レンダラを組み合わせた勾配法ベースのベクタ画像生成
論文本体・著者
解きたい問題
新規性
実装
実験・議論
入力テキストに近づけるだけではなく、特定のワード(Negative Prompt)から離すような損失を追加することで生成される絵をある程度コントロールできた
議論
読んだ中での不明点などの感想
関連論文
The text was updated successfully, but these errors were encountered: