语义感知生成多视角人像画（英文版）

英文标题：Semantic-aware Generation of Multi-view Portrait Drawings中文摘要：本文提出了一种语义感知生成器（SAGE），用于综合多视角人像绘画，该方法可通过多视角语义图进一步细化生成结果，并应用于多种艺术风格的生成，实验结果表明，相比现有的三维感知图像综合方法，SAGE 达到了更卓越或高竞争性的性能。英文摘要：Neural radiance fields (NeRF) based methods have shown amazing performance insynthesizing 3D-consistent photographic images, but fail to generate multi-viewportrait drawings. The key is that the basic assumption of these methods -- asurface point is consistent when rendered from different views -- doesn't holdfor d