Drawing images of characters with desired poses is an essential but laborious task in anime production. In this paper, we present the Collaborative Neural Rendering (CoNR) method, which creates new images for specified poses from a few reference images (AKA Character Sheets). In general, the high diversity of body shapes of anime characters defies the employment of universal body models like SMPL, which are developed from real-world humans. To overcome this difficulty, CoNR uses a compact and easy-to-obtain landmark encoding to avoid creating a unified UV mapping in the pipeline. In addition, the performance of CoNR can be significantly improved when referring to multiple reference images, thanks to feature space cross-view warping in a carefully designed neural network. Moreover, we have collected a character sheet dataset containing over 700,000 hand-drawn and synthesized images of diverse poses to facilitate research in this area. Our code and demo are available at https://github.com/megvii-research/CoNR.

翻译：绘制带有理想外形的字符图像是动脉制作中一项必要但艰巨的任务。 在本文中,我们介绍了合作神经成像(CONR)方法,该方法为一些参考图像(AKA字符表)中的具体成像创造了新的图像。一般而言,动脉字符形的高度多样性,无法使用由现实世界人类开发的SMPL等通用体模型。为了克服这一困难,CNR使用一个简单易懂的紧凑标志编码,以避免在管道中创建统一的紫外线绘图。此外,在提及多维图像时,CONR的性能可以大大改进,因为这是一个精心设计的神经网络中的空间交叉视图旋转特征。此外,我们收集了一个包含700,000多个手绘和合成的多种外形图像的字符表数据集,以便利这一领域的研究。我们的代码和演示可在https://github.com/megvii-research/CONR。