English(EN) Generating 3D models from sketches of human faces using a combined approach of Convolutional Neural Networks, Procedural Modeling, and Contour Mapping

新方法从草图生成3D面部模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-26 04:00

研究人员开发了一种从2D草图生成人类面部3D模型的新方法。该方法集成了用于表情检测的卷积神经网络（CNN）、一个名为Valley Girl的参数化3D面部模型以及活动蛇形轮廓。CNN组件经过训练，通过检测FACS Action Units来识别面部表情，然后将其应用于Valley Girl模型。最后，使用活动蛇形轮廓来优化生成的3D模型，使其与原始草图的轮廓匹配。 AI

影响这项研究通过能够从简单的草图中更快地生成详细的面部模型，有可能为艺术家和开发人员简化3D角色创建。

排序理由该集群包含一篇详细介绍3D模型生成新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Nancy Iskander · 2026-05-26 04:00

Generating 3D models from sketches of human faces using a combined approach of Convolutional Neural Networks, Procedural Modeling, and Contour Mapping

arXiv:2605.25418v1 Announce Type: cross Abstract: Generating 3D models from face sketches is an active topic of research in Computer Graphics due to its potential to tremendously facilitate the modeling of faces for both professional 3D arists and novices. Motivated by the observ…

报道来源 [1]

Generating 3D models from sketches of human faces using a combined approach of Convolutional Neural Networks, Procedural Modeling, and Contour Mapping

相关实体

相关话题